Upload . with huggingface_hub
Browse files
.summary/0/events.out.tfevents.1677256351.groot
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a27689e2b15480c7b0de5331930fc6b2010a5e5cfdf6996514477550a12a9a7e
|
| 3 |
+
size 274896
|
README.md
CHANGED
|
@@ -15,7 +15,7 @@ model-index:
|
|
| 15 |
type: doom_health_gathering_supreme
|
| 16 |
metrics:
|
| 17 |
- type: mean_reward
|
| 18 |
-
value:
|
| 19 |
name: mean_reward
|
| 20 |
verified: false
|
| 21 |
---
|
|
|
|
| 15 |
type: doom_health_gathering_supreme
|
| 16 |
metrics:
|
| 17 |
- type: mean_reward
|
| 18 |
+
value: 12.83 +/- 5.79
|
| 19 |
name: mean_reward
|
| 20 |
verified: false
|
| 21 |
---
|
checkpoint_p0/best_000004690_19210240_reward_36.140.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0ac1e8ee163b7c6b2a110e18c0d1ced65ac0ae2983da4c8c1335bd8c61d0973
|
| 3 |
+
size 34928806
|
checkpoint_p0/checkpoint_000004490_18391040.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:875159c7a36195f02acf6830029cff46f66e2ecfae772e6dc7d6d6a1626a5af1
|
| 3 |
+
size 34929220
|
checkpoint_p0/checkpoint_000004884_20004864.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b950aee279a8b057e6fafcaf971319d0a08f04204d745e26ed51c2e419a7398
|
| 3 |
+
size 34929220
|
config.json
CHANGED
|
@@ -15,8 +15,8 @@
|
|
| 15 |
"worker_num_splits": 2,
|
| 16 |
"policy_workers_per_policy": 1,
|
| 17 |
"max_policy_lag": 1000,
|
| 18 |
-
"num_workers":
|
| 19 |
-
"num_envs_per_worker":
|
| 20 |
"batch_size": 1024,
|
| 21 |
"num_batches_per_epoch": 1,
|
| 22 |
"num_epochs": 1,
|
|
@@ -65,7 +65,7 @@
|
|
| 65 |
"summaries_use_frameskip": true,
|
| 66 |
"heartbeat_interval": 20,
|
| 67 |
"heartbeat_reporting_interval": 600,
|
| 68 |
-
"train_for_env_steps":
|
| 69 |
"train_for_seconds": 10000000000,
|
| 70 |
"save_every_sec": 120,
|
| 71 |
"keep_checkpoints": 2,
|
|
|
|
| 15 |
"worker_num_splits": 2,
|
| 16 |
"policy_workers_per_policy": 1,
|
| 17 |
"max_policy_lag": 1000,
|
| 18 |
+
"num_workers": 16,
|
| 19 |
+
"num_envs_per_worker": 6,
|
| 20 |
"batch_size": 1024,
|
| 21 |
"num_batches_per_epoch": 1,
|
| 22 |
"num_epochs": 1,
|
|
|
|
| 65 |
"summaries_use_frameskip": true,
|
| 66 |
"heartbeat_interval": 20,
|
| 67 |
"heartbeat_reporting_interval": 600,
|
| 68 |
+
"train_for_env_steps": 20000000,
|
| 69 |
"train_for_seconds": 10000000000,
|
| 70 |
"save_every_sec": 120,
|
| 71 |
"keep_checkpoints": 2,
|
replay.mp4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9cf58ae42597207ce5c99f41b3d124ec0325bb4240a29954b4674bf2c479acb8
|
| 3 |
+
size 25052505
|
sf_log.txt
CHANGED
|
@@ -404,3 +404,1115 @@ save_policy_outputs: 6.1360
|
|
| 404 |
[2023-02-24 17:13:46,714][2343622] Runner profile tree view:
|
| 405 |
main_loop: 151.8999
|
| 406 |
[2023-02-24 17:13:46,715][2343622] Collected {0: 4005888}, FPS: 26371.9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 404 |
[2023-02-24 17:13:46,714][2343622] Runner profile tree view:
|
| 405 |
main_loop: 151.8999
|
| 406 |
[2023-02-24 17:13:46,715][2343622] Collected {0: 4005888}, FPS: 26371.9
|
| 407 |
+
[2023-02-24 17:32:32,877][2364708] Saving configuration to /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/config.json...
|
| 408 |
+
[2023-02-24 17:32:32,878][2364708] Rollout worker 0 uses device cpu
|
| 409 |
+
[2023-02-24 17:32:32,878][2364708] Rollout worker 1 uses device cpu
|
| 410 |
+
[2023-02-24 17:32:32,878][2364708] Rollout worker 2 uses device cpu
|
| 411 |
+
[2023-02-24 17:32:32,878][2364708] Rollout worker 3 uses device cpu
|
| 412 |
+
[2023-02-24 17:32:32,878][2364708] Rollout worker 4 uses device cpu
|
| 413 |
+
[2023-02-24 17:32:32,879][2364708] Rollout worker 5 uses device cpu
|
| 414 |
+
[2023-02-24 17:32:32,879][2364708] Rollout worker 6 uses device cpu
|
| 415 |
+
[2023-02-24 17:32:32,879][2364708] Rollout worker 7 uses device cpu
|
| 416 |
+
[2023-02-24 17:32:32,879][2364708] Rollout worker 8 uses device cpu
|
| 417 |
+
[2023-02-24 17:32:32,879][2364708] Rollout worker 9 uses device cpu
|
| 418 |
+
[2023-02-24 17:32:32,879][2364708] Rollout worker 10 uses device cpu
|
| 419 |
+
[2023-02-24 17:32:32,879][2364708] Rollout worker 11 uses device cpu
|
| 420 |
+
[2023-02-24 17:32:32,879][2364708] Rollout worker 12 uses device cpu
|
| 421 |
+
[2023-02-24 17:32:32,880][2364708] Rollout worker 13 uses device cpu
|
| 422 |
+
[2023-02-24 17:32:32,880][2364708] Rollout worker 14 uses device cpu
|
| 423 |
+
[2023-02-24 17:32:32,880][2364708] Rollout worker 15 uses device cpu
|
| 424 |
+
[2023-02-24 17:32:32,936][2364708] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 425 |
+
[2023-02-24 17:32:32,936][2364708] InferenceWorker_p0-w0: min num requests: 5
|
| 426 |
+
[2023-02-24 17:32:32,970][2364708] Starting all processes...
|
| 427 |
+
[2023-02-24 17:32:32,970][2364708] Starting process learner_proc0
|
| 428 |
+
[2023-02-24 17:32:33,717][2364708] Starting all processes...
|
| 429 |
+
[2023-02-24 17:32:33,721][2364708] Starting process inference_proc0-0
|
| 430 |
+
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc0
|
| 431 |
+
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc1
|
| 432 |
+
[2023-02-24 17:32:33,722][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 433 |
+
[2023-02-24 17:32:33,722][2364791] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
| 434 |
+
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc2
|
| 435 |
+
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc3
|
| 436 |
+
[2023-02-24 17:32:33,721][2364708] Starting process rollout_proc4
|
| 437 |
+
[2023-02-24 17:32:33,722][2364708] Starting process rollout_proc5
|
| 438 |
+
[2023-02-24 17:32:33,722][2364708] Starting process rollout_proc6
|
| 439 |
+
[2023-02-24 17:32:33,723][2364708] Starting process rollout_proc7
|
| 440 |
+
[2023-02-24 17:32:33,726][2364708] Starting process rollout_proc8
|
| 441 |
+
[2023-02-24 17:32:33,727][2364708] Starting process rollout_proc9
|
| 442 |
+
[2023-02-24 17:32:33,739][2364791] Num visible devices: 1
|
| 443 |
+
[2023-02-24 17:32:33,728][2364708] Starting process rollout_proc10
|
| 444 |
+
[2023-02-24 17:32:33,729][2364708] Starting process rollout_proc11
|
| 445 |
+
[2023-02-24 17:32:33,729][2364708] Starting process rollout_proc12
|
| 446 |
+
[2023-02-24 17:32:33,729][2364708] Starting process rollout_proc13
|
| 447 |
+
[2023-02-24 17:32:33,796][2364791] Starting seed is not provided
|
| 448 |
+
[2023-02-24 17:32:33,796][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 449 |
+
[2023-02-24 17:32:33,797][2364791] Initializing actor-critic model on device cuda:0
|
| 450 |
+
[2023-02-24 17:32:33,797][2364791] RunningMeanStd input shape: (3, 72, 128)
|
| 451 |
+
[2023-02-24 17:32:33,798][2364791] RunningMeanStd input shape: (1,)
|
| 452 |
+
[2023-02-24 17:32:33,730][2364708] Starting process rollout_proc14
|
| 453 |
+
[2023-02-24 17:32:33,813][2364791] ConvEncoder: input_channels=3
|
| 454 |
+
[2023-02-24 17:32:34,006][2364791] Conv encoder output size: 512
|
| 455 |
+
[2023-02-24 17:32:34,023][2364791] Policy head output size: 512
|
| 456 |
+
[2023-02-24 17:32:34,038][2364791] Created Actor Critic model with architecture:
|
| 457 |
+
[2023-02-24 17:32:34,050][2364791] ActorCriticSharedWeights(
|
| 458 |
+
(obs_normalizer): ObservationNormalizer(
|
| 459 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
| 460 |
+
(running_mean_std): ModuleDict(
|
| 461 |
+
(obs): RunningMeanStdInPlace()
|
| 462 |
+
)
|
| 463 |
+
)
|
| 464 |
+
)
|
| 465 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
| 466 |
+
(encoder): VizdoomEncoder(
|
| 467 |
+
(basic_encoder): ConvEncoder(
|
| 468 |
+
(enc): RecursiveScriptModule(
|
| 469 |
+
original_name=ConvEncoderImpl
|
| 470 |
+
(conv_head): RecursiveScriptModule(
|
| 471 |
+
original_name=Sequential
|
| 472 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
| 473 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
| 474 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
| 475 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
| 476 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
| 477 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
| 478 |
+
)
|
| 479 |
+
(mlp_layers): RecursiveScriptModule(
|
| 480 |
+
original_name=Sequential
|
| 481 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
| 482 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
| 483 |
+
)
|
| 484 |
+
)
|
| 485 |
+
)
|
| 486 |
+
)
|
| 487 |
+
(core): ModelCoreRNN(
|
| 488 |
+
(core): GRU(512, 512)
|
| 489 |
+
)
|
| 490 |
+
(decoder): MlpDecoder(
|
| 491 |
+
(mlp): Identity()
|
| 492 |
+
)
|
| 493 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
| 494 |
+
(action_parameterization): ActionParameterizationDefault(
|
| 495 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
| 496 |
+
)
|
| 497 |
+
)
|
| 498 |
+
[2023-02-24 17:32:35,405][2364708] Starting process rollout_proc15
|
| 499 |
+
[2023-02-24 17:32:35,416][2364834] Worker 2 uses CPU cores [2]
|
| 500 |
+
[2023-02-24 17:32:35,418][2364833] Worker 1 uses CPU cores [1]
|
| 501 |
+
[2023-02-24 17:32:35,490][2364839] Worker 7 uses CPU cores [7]
|
| 502 |
+
[2023-02-24 17:32:35,500][2364855] Worker 10 uses CPU cores [10]
|
| 503 |
+
[2023-02-24 17:32:35,502][2364832] Worker 0 uses CPU cores [0]
|
| 504 |
+
[2023-02-24 17:32:35,502][2364831] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 505 |
+
[2023-02-24 17:32:35,503][2364831] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
| 506 |
+
[2023-02-24 17:32:35,518][2364838] Worker 6 uses CPU cores [6]
|
| 507 |
+
[2023-02-24 17:32:35,519][2364831] Num visible devices: 1
|
| 508 |
+
[2023-02-24 17:32:35,530][2364862] Worker 14 uses CPU cores [14]
|
| 509 |
+
[2023-02-24 17:32:35,534][2364860] Worker 12 uses CPU cores [12]
|
| 510 |
+
[2023-02-24 17:32:35,554][2364835] Worker 4 uses CPU cores [4]
|
| 511 |
+
[2023-02-24 17:32:35,573][2364861] Worker 13 uses CPU cores [13]
|
| 512 |
+
[2023-02-24 17:32:35,598][2364859] Worker 8 uses CPU cores [8]
|
| 513 |
+
[2023-02-24 17:32:35,642][2364836] Worker 3 uses CPU cores [3]
|
| 514 |
+
[2023-02-24 17:32:35,643][2364837] Worker 5 uses CPU cores [5]
|
| 515 |
+
[2023-02-24 17:32:35,661][2364856] Worker 9 uses CPU cores [9]
|
| 516 |
+
[2023-02-24 17:32:35,712][2364857] Worker 11 uses CPU cores [11]
|
| 517 |
+
[2023-02-24 17:32:36,334][2365108] Worker 15 uses CPU cores [15]
|
| 518 |
+
[2023-02-24 17:32:36,424][2364791] Using optimizer <class 'torch.optim.adam.Adam'>
|
| 519 |
+
[2023-02-24 17:32:36,424][2364791] Loading state from checkpoint /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
| 520 |
+
[2023-02-24 17:32:36,444][2364791] Loading model from checkpoint
|
| 521 |
+
[2023-02-24 17:32:36,447][2364791] Loaded experiment state at self.train_step=978, self.env_steps=4005888
|
| 522 |
+
[2023-02-24 17:32:36,447][2364791] Initialized policy 0 weights for model version 978
|
| 523 |
+
[2023-02-24 17:32:36,449][2364791] LearnerWorker_p0 finished initialization!
|
| 524 |
+
[2023-02-24 17:32:36,449][2364791] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
| 525 |
+
[2023-02-24 17:32:36,525][2364831] RunningMeanStd input shape: (3, 72, 128)
|
| 526 |
+
[2023-02-24 17:32:36,525][2364831] RunningMeanStd input shape: (1,)
|
| 527 |
+
[2023-02-24 17:32:36,532][2364831] ConvEncoder: input_channels=3
|
| 528 |
+
[2023-02-24 17:32:36,595][2364831] Conv encoder output size: 512
|
| 529 |
+
[2023-02-24 17:32:36,595][2364831] Policy head output size: 512
|
| 530 |
+
[2023-02-24 17:32:37,849][2364708] Inference worker 0-0 is ready!
|
| 531 |
+
[2023-02-24 17:32:37,849][2364708] All inference workers are ready! Signal rollout workers to start!
|
| 532 |
+
[2023-02-24 17:32:37,887][2364862] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 533 |
+
[2023-02-24 17:32:37,887][2364836] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 534 |
+
[2023-02-24 17:32:37,888][2364833] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 535 |
+
[2023-02-24 17:32:37,888][2364835] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 536 |
+
[2023-02-24 17:32:37,888][2364832] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 537 |
+
[2023-02-24 17:32:37,888][2364859] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 538 |
+
[2023-02-24 17:32:37,887][2364857] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 539 |
+
[2023-02-24 17:32:37,889][2364856] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 540 |
+
[2023-02-24 17:32:37,889][2364837] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 541 |
+
[2023-02-24 17:32:37,889][2365108] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 542 |
+
[2023-02-24 17:32:37,889][2364839] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 543 |
+
[2023-02-24 17:32:37,889][2364860] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 544 |
+
[2023-02-24 17:32:37,887][2364855] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 545 |
+
[2023-02-24 17:32:37,888][2364861] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 546 |
+
[2023-02-24 17:32:37,888][2364834] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 547 |
+
[2023-02-24 17:32:37,892][2364838] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 548 |
+
[2023-02-24 17:32:38,292][2364855] Decorrelating experience for 0 frames...
|
| 549 |
+
[2023-02-24 17:32:38,293][2364833] Decorrelating experience for 0 frames...
|
| 550 |
+
[2023-02-24 17:32:38,294][2364857] Decorrelating experience for 0 frames...
|
| 551 |
+
[2023-02-24 17:32:38,294][2364836] Decorrelating experience for 0 frames...
|
| 552 |
+
[2023-02-24 17:32:38,295][2364834] Decorrelating experience for 0 frames...
|
| 553 |
+
[2023-02-24 17:32:38,295][2364856] Decorrelating experience for 0 frames...
|
| 554 |
+
[2023-02-24 17:32:38,296][2364859] Decorrelating experience for 0 frames...
|
| 555 |
+
[2023-02-24 17:32:38,296][2364832] Decorrelating experience for 0 frames...
|
| 556 |
+
[2023-02-24 17:32:38,484][2364856] Decorrelating experience for 32 frames...
|
| 557 |
+
[2023-02-24 17:32:38,511][2364862] Decorrelating experience for 0 frames...
|
| 558 |
+
[2023-02-24 17:32:38,516][2364861] Decorrelating experience for 0 frames...
|
| 559 |
+
[2023-02-24 17:32:38,517][2364835] Decorrelating experience for 0 frames...
|
| 560 |
+
[2023-02-24 17:32:38,517][2364839] Decorrelating experience for 0 frames...
|
| 561 |
+
[2023-02-24 17:32:38,585][2364834] Decorrelating experience for 32 frames...
|
| 562 |
+
[2023-02-24 17:32:38,617][2364857] Decorrelating experience for 32 frames...
|
| 563 |
+
[2023-02-24 17:32:38,617][2364836] Decorrelating experience for 32 frames...
|
| 564 |
+
[2023-02-24 17:32:38,628][2364855] Decorrelating experience for 32 frames...
|
| 565 |
+
[2023-02-24 17:32:38,697][2364856] Decorrelating experience for 64 frames...
|
| 566 |
+
[2023-02-24 17:32:38,700][2364862] Decorrelating experience for 32 frames...
|
| 567 |
+
[2023-02-24 17:32:38,719][2364832] Decorrelating experience for 32 frames...
|
| 568 |
+
[2023-02-24 17:32:38,821][2364857] Decorrelating experience for 64 frames...
|
| 569 |
+
[2023-02-24 17:32:38,827][2364835] Decorrelating experience for 32 frames...
|
| 570 |
+
[2023-02-24 17:32:38,834][2364860] Decorrelating experience for 0 frames...
|
| 571 |
+
[2023-02-24 17:32:38,844][2364834] Decorrelating experience for 64 frames...
|
| 572 |
+
[2023-02-24 17:32:38,858][2364861] Decorrelating experience for 32 frames...
|
| 573 |
+
[2023-02-24 17:32:38,877][2364859] Decorrelating experience for 32 frames...
|
| 574 |
+
[2023-02-24 17:32:38,926][2364856] Decorrelating experience for 96 frames...
|
| 575 |
+
[2023-02-24 17:32:39,022][2364860] Decorrelating experience for 32 frames...
|
| 576 |
+
[2023-02-24 17:32:39,026][2364837] Decorrelating experience for 0 frames...
|
| 577 |
+
[2023-02-24 17:32:39,041][2364832] Decorrelating experience for 64 frames...
|
| 578 |
+
[2023-02-24 17:32:39,129][2365108] Decorrelating experience for 0 frames...
|
| 579 |
+
[2023-02-24 17:32:39,155][2364839] Decorrelating experience for 32 frames...
|
| 580 |
+
[2023-02-24 17:32:39,180][2364861] Decorrelating experience for 64 frames...
|
| 581 |
+
[2023-02-24 17:32:39,263][2364832] Decorrelating experience for 96 frames...
|
| 582 |
+
[2023-02-24 17:32:39,298][2364837] Decorrelating experience for 32 frames...
|
| 583 |
+
[2023-02-24 17:32:39,332][2364835] Decorrelating experience for 64 frames...
|
| 584 |
+
[2023-02-24 17:32:39,336][2364836] Decorrelating experience for 64 frames...
|
| 585 |
+
[2023-02-24 17:32:39,359][2364857] Decorrelating experience for 96 frames...
|
| 586 |
+
[2023-02-24 17:32:39,365][2364838] Decorrelating experience for 0 frames...
|
| 587 |
+
[2023-02-24 17:32:39,378][2364834] Decorrelating experience for 96 frames...
|
| 588 |
+
[2023-02-24 17:32:39,523][2365108] Decorrelating experience for 32 frames...
|
| 589 |
+
[2023-02-24 17:32:39,535][2364833] Decorrelating experience for 32 frames...
|
| 590 |
+
[2023-02-24 17:32:39,552][2364862] Decorrelating experience for 64 frames...
|
| 591 |
+
[2023-02-24 17:32:39,593][2364857] Decorrelating experience for 128 frames...
|
| 592 |
+
[2023-02-24 17:32:39,623][2364861] Decorrelating experience for 96 frames...
|
| 593 |
+
[2023-02-24 17:32:39,682][2364835] Decorrelating experience for 96 frames...
|
| 594 |
+
[2023-02-24 17:32:39,695][2364860] Decorrelating experience for 64 frames...
|
| 595 |
+
[2023-02-24 17:32:39,708][2364837] Decorrelating experience for 64 frames...
|
| 596 |
+
[2023-02-24 17:32:39,748][2364856] Decorrelating experience for 128 frames...
|
| 597 |
+
[2023-02-24 17:32:39,783][2364862] Decorrelating experience for 96 frames...
|
| 598 |
+
[2023-02-24 17:32:39,789][2364832] Decorrelating experience for 128 frames...
|
| 599 |
+
[2023-02-24 17:32:39,875][2364857] Decorrelating experience for 160 frames...
|
| 600 |
+
[2023-02-24 17:32:39,884][2364855] Decorrelating experience for 64 frames...
|
| 601 |
+
[2023-02-24 17:32:39,898][2364861] Decorrelating experience for 128 frames...
|
| 602 |
+
[2023-02-24 17:32:39,924][2364859] Decorrelating experience for 64 frames...
|
| 603 |
+
[2023-02-24 17:32:40,010][2364838] Decorrelating experience for 32 frames...
|
| 604 |
+
[2023-02-24 17:32:40,043][2365108] Decorrelating experience for 64 frames...
|
| 605 |
+
[2023-02-24 17:32:40,047][2364856] Decorrelating experience for 160 frames...
|
| 606 |
+
[2023-02-24 17:32:40,051][2364860] Decorrelating experience for 96 frames...
|
| 607 |
+
[2023-02-24 17:32:40,070][2364839] Decorrelating experience for 64 frames...
|
| 608 |
+
[2023-02-24 17:32:40,088][2364835] Decorrelating experience for 128 frames...
|
| 609 |
+
[2023-02-24 17:32:40,123][2364834] Decorrelating experience for 128 frames...
|
| 610 |
+
[2023-02-24 17:32:40,183][2364833] Decorrelating experience for 64 frames...
|
| 611 |
+
[2023-02-24 17:32:40,213][2364859] Decorrelating experience for 96 frames...
|
| 612 |
+
[2023-02-24 17:32:40,319][2364838] Decorrelating experience for 64 frames...
|
| 613 |
+
[2023-02-24 17:32:40,333][2364835] Decorrelating experience for 160 frames...
|
| 614 |
+
[2023-02-24 17:32:40,337][2364832] Decorrelating experience for 160 frames...
|
| 615 |
+
[2023-02-24 17:32:40,372][2364862] Decorrelating experience for 128 frames...
|
| 616 |
+
[2023-02-24 17:32:40,404][2364861] Decorrelating experience for 160 frames...
|
| 617 |
+
[2023-02-24 17:32:40,429][2364837] Decorrelating experience for 96 frames...
|
| 618 |
+
[2023-02-24 17:32:40,514][2365108] Decorrelating experience for 96 frames...
|
| 619 |
+
[2023-02-24 17:32:40,535][2364839] Decorrelating experience for 96 frames...
|
| 620 |
+
[2023-02-24 17:32:40,595][2364834] Decorrelating experience for 160 frames...
|
| 621 |
+
[2023-02-24 17:32:40,629][2364860] Decorrelating experience for 128 frames...
|
| 622 |
+
[2023-02-24 17:32:40,640][2364833] Decorrelating experience for 96 frames...
|
| 623 |
+
[2023-02-24 17:32:40,643][2364859] Decorrelating experience for 128 frames...
|
| 624 |
+
[2023-02-24 17:32:40,748][2364838] Decorrelating experience for 96 frames...
|
| 625 |
+
[2023-02-24 17:32:40,777][2365108] Decorrelating experience for 128 frames...
|
| 626 |
+
[2023-02-24 17:32:40,793][2364836] Decorrelating experience for 96 frames...
|
| 627 |
+
[2023-02-24 17:32:40,912][2364837] Decorrelating experience for 128 frames...
|
| 628 |
+
[2023-02-24 17:32:40,918][2364791] Signal inference workers to stop experience collection...
|
| 629 |
+
[2023-02-24 17:32:40,922][2364831] InferenceWorker_p0-w0: stopping experience collection
|
| 630 |
+
[2023-02-24 17:32:40,955][2364860] Decorrelating experience for 160 frames...
|
| 631 |
+
[2023-02-24 17:32:40,971][2364859] Decorrelating experience for 160 frames...
|
| 632 |
+
[2023-02-24 17:32:41,025][2364833] Decorrelating experience for 128 frames...
|
| 633 |
+
[2023-02-24 17:32:41,056][2364836] Decorrelating experience for 128 frames...
|
| 634 |
+
[2023-02-24 17:32:41,076][2364838] Decorrelating experience for 128 frames...
|
| 635 |
+
[2023-02-24 17:32:41,132][2365108] Decorrelating experience for 160 frames...
|
| 636 |
+
[2023-02-24 17:32:41,199][2364837] Decorrelating experience for 160 frames...
|
| 637 |
+
[2023-02-24 17:32:41,202][2364862] Decorrelating experience for 160 frames...
|
| 638 |
+
[2023-02-24 17:32:41,266][2364708] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 2304. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
|
| 639 |
+
[2023-02-24 17:32:41,266][2364708] Avg episode reward: [(0, '1.871')]
|
| 640 |
+
[2023-02-24 17:32:41,343][2364839] Decorrelating experience for 128 frames...
|
| 641 |
+
[2023-02-24 17:32:41,343][2364836] Decorrelating experience for 160 frames...
|
| 642 |
+
[2023-02-24 17:32:41,392][2364838] Decorrelating experience for 160 frames...
|
| 643 |
+
[2023-02-24 17:32:41,443][2364855] Decorrelating experience for 96 frames...
|
| 644 |
+
[2023-02-24 17:32:41,569][2364833] Decorrelating experience for 160 frames...
|
| 645 |
+
[2023-02-24 17:32:41,656][2364855] Decorrelating experience for 128 frames...
|
| 646 |
+
[2023-02-24 17:32:41,671][2364839] Decorrelating experience for 160 frames...
|
| 647 |
+
[2023-02-24 17:32:41,801][2364791] Signal inference workers to resume experience collection...
|
| 648 |
+
[2023-02-24 17:32:41,801][2364831] InferenceWorker_p0-w0: resuming experience collection
|
| 649 |
+
[2023-02-24 17:32:41,877][2364855] Decorrelating experience for 160 frames...
|
| 650 |
+
[2023-02-24 17:32:43,213][2364831] Updated weights for policy 0, policy_version 988 (0.0223)
|
| 651 |
+
[2023-02-24 17:32:44,160][2364831] Updated weights for policy 0, policy_version 998 (0.0009)
|
| 652 |
+
[2023-02-24 17:32:45,129][2364831] Updated weights for policy 0, policy_version 1008 (0.0011)
|
| 653 |
+
[2023-02-24 17:32:46,071][2364831] Updated weights for policy 0, policy_version 1018 (0.0009)
|
| 654 |
+
[2023-02-24 17:32:46,266][2364708] Fps is (10 sec: 33586.6, 60 sec: 33586.6, 300 sec: 33586.6). Total num frames: 4173824. Throughput: 0: 3350.3. Samples: 19056. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 655 |
+
[2023-02-24 17:32:46,266][2364708] Avg episode reward: [(0, '18.870')]
|
| 656 |
+
[2023-02-24 17:32:47,062][2364831] Updated weights for policy 0, policy_version 1028 (0.0009)
|
| 657 |
+
[2023-02-24 17:32:48,070][2364831] Updated weights for policy 0, policy_version 1038 (0.0012)
|
| 658 |
+
[2023-02-24 17:32:49,031][2364831] Updated weights for policy 0, policy_version 1048 (0.0009)
|
| 659 |
+
[2023-02-24 17:32:50,044][2364831] Updated weights for policy 0, policy_version 1058 (0.0016)
|
| 660 |
+
[2023-02-24 17:32:50,993][2364831] Updated weights for policy 0, policy_version 1068 (0.0013)
|
| 661 |
+
[2023-02-24 17:32:51,266][2364708] Fps is (10 sec: 37683.0, 60 sec: 37683.0, 300 sec: 37683.0). Total num frames: 4382720. Throughput: 0: 7973.1. Samples: 82035. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 662 |
+
[2023-02-24 17:32:51,266][2364708] Avg episode reward: [(0, '24.692')]
|
| 663 |
+
[2023-02-24 17:32:51,978][2364831] Updated weights for policy 0, policy_version 1078 (0.0010)
|
| 664 |
+
[2023-02-24 17:32:52,932][2364708] Heartbeat connected on Batcher_0
|
| 665 |
+
[2023-02-24 17:32:52,934][2364708] Heartbeat connected on LearnerWorker_p0
|
| 666 |
+
[2023-02-24 17:32:52,941][2364708] Heartbeat connected on InferenceWorker_p0-w0
|
| 667 |
+
[2023-02-24 17:32:52,944][2364708] Heartbeat connected on RolloutWorker_w2
|
| 668 |
+
[2023-02-24 17:32:52,945][2364708] Heartbeat connected on RolloutWorker_w3
|
| 669 |
+
[2023-02-24 17:32:52,949][2364708] Heartbeat connected on RolloutWorker_w4
|
| 670 |
+
[2023-02-24 17:32:52,949][2364708] Heartbeat connected on RolloutWorker_w5
|
| 671 |
+
[2023-02-24 17:32:52,953][2364708] Heartbeat connected on RolloutWorker_w6
|
| 672 |
+
[2023-02-24 17:32:52,953][2364708] Heartbeat connected on RolloutWorker_w7
|
| 673 |
+
[2023-02-24 17:32:52,955][2364708] Heartbeat connected on RolloutWorker_w0
|
| 674 |
+
[2023-02-24 17:32:52,955][2364708] Heartbeat connected on RolloutWorker_w1
|
| 675 |
+
[2023-02-24 17:32:52,957][2364708] Heartbeat connected on RolloutWorker_w8
|
| 676 |
+
[2023-02-24 17:32:52,958][2364708] Heartbeat connected on RolloutWorker_w9
|
| 677 |
+
[2023-02-24 17:32:52,962][2364708] Heartbeat connected on RolloutWorker_w10
|
| 678 |
+
[2023-02-24 17:32:52,963][2364708] Heartbeat connected on RolloutWorker_w11
|
| 679 |
+
[2023-02-24 17:32:52,966][2364708] Heartbeat connected on RolloutWorker_w13
|
| 680 |
+
[2023-02-24 17:32:52,967][2364708] Heartbeat connected on RolloutWorker_w12
|
| 681 |
+
[2023-02-24 17:32:52,968][2364708] Heartbeat connected on RolloutWorker_w14
|
| 682 |
+
[2023-02-24 17:32:52,981][2364708] Heartbeat connected on RolloutWorker_w15
|
| 683 |
+
[2023-02-24 17:32:52,981][2364831] Updated weights for policy 0, policy_version 1088 (0.0012)
|
| 684 |
+
[2023-02-24 17:32:53,959][2364831] Updated weights for policy 0, policy_version 1098 (0.0010)
|
| 685 |
+
[2023-02-24 17:32:54,954][2364831] Updated weights for policy 0, policy_version 1108 (0.0009)
|
| 686 |
+
[2023-02-24 17:32:55,930][2364831] Updated weights for policy 0, policy_version 1118 (0.0011)
|
| 687 |
+
[2023-02-24 17:32:56,266][2364708] Fps is (10 sec: 41779.4, 60 sec: 39048.4, 300 sec: 39048.4). Total num frames: 4591616. Throughput: 0: 9485.2. Samples: 144582. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 688 |
+
[2023-02-24 17:32:56,266][2364708] Avg episode reward: [(0, '25.204')]
|
| 689 |
+
[2023-02-24 17:32:56,266][2364791] Saving new best policy, reward=25.204!
|
| 690 |
+
[2023-02-24 17:32:56,911][2364831] Updated weights for policy 0, policy_version 1128 (0.0014)
|
| 691 |
+
[2023-02-24 17:32:57,948][2364831] Updated weights for policy 0, policy_version 1138 (0.0011)
|
| 692 |
+
[2023-02-24 17:32:58,912][2364831] Updated weights for policy 0, policy_version 1148 (0.0011)
|
| 693 |
+
[2023-02-24 17:32:59,887][2364831] Updated weights for policy 0, policy_version 1158 (0.0012)
|
| 694 |
+
[2023-02-24 17:33:00,871][2364831] Updated weights for policy 0, policy_version 1168 (0.0016)
|
| 695 |
+
[2023-02-24 17:33:01,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 39526.2, 300 sec: 39526.2). Total num frames: 4796416. Throughput: 0: 8660.6. Samples: 175518. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 696 |
+
[2023-02-24 17:33:01,266][2364708] Avg episode reward: [(0, '24.312')]
|
| 697 |
+
[2023-02-24 17:33:01,888][2364831] Updated weights for policy 0, policy_version 1178 (0.0009)
|
| 698 |
+
[2023-02-24 17:33:02,860][2364831] Updated weights for policy 0, policy_version 1188 (0.0009)
|
| 699 |
+
[2023-02-24 17:33:03,875][2364831] Updated weights for policy 0, policy_version 1198 (0.0014)
|
| 700 |
+
[2023-02-24 17:33:04,853][2364831] Updated weights for policy 0, policy_version 1208 (0.0009)
|
| 701 |
+
[2023-02-24 17:33:05,857][2364831] Updated weights for policy 0, policy_version 1218 (0.0012)
|
| 702 |
+
[2023-02-24 17:33:06,266][2364708] Fps is (10 sec: 41368.6, 60 sec: 39976.5, 300 sec: 39976.5). Total num frames: 5005312. Throughput: 0: 9410.3. Samples: 237564. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 703 |
+
[2023-02-24 17:33:06,266][2364708] Avg episode reward: [(0, '24.517')]
|
| 704 |
+
[2023-02-24 17:33:06,796][2364831] Updated weights for policy 0, policy_version 1228 (0.0011)
|
| 705 |
+
[2023-02-24 17:33:07,774][2364831] Updated weights for policy 0, policy_version 1238 (0.0011)
|
| 706 |
+
[2023-02-24 17:33:08,779][2364831] Updated weights for policy 0, policy_version 1248 (0.0012)
|
| 707 |
+
[2023-02-24 17:33:09,772][2364831] Updated weights for policy 0, policy_version 1258 (0.0010)
|
| 708 |
+
[2023-02-24 17:33:10,736][2364831] Updated weights for policy 0, policy_version 1268 (0.0014)
|
| 709 |
+
[2023-02-24 17:33:11,266][2364708] Fps is (10 sec: 41779.2, 60 sec: 40277.2, 300 sec: 40277.2). Total num frames: 5214208. Throughput: 0: 9920.8. Samples: 299928. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 710 |
+
[2023-02-24 17:33:11,266][2364708] Avg episode reward: [(0, '30.044')]
|
| 711 |
+
[2023-02-24 17:33:11,269][2364791] Saving new best policy, reward=30.044!
|
| 712 |
+
[2023-02-24 17:33:11,776][2364831] Updated weights for policy 0, policy_version 1278 (0.0009)
|
| 713 |
+
[2023-02-24 17:33:12,732][2364831] Updated weights for policy 0, policy_version 1288 (0.0009)
|
| 714 |
+
[2023-02-24 17:33:13,718][2364831] Updated weights for policy 0, policy_version 1298 (0.0014)
|
| 715 |
+
[2023-02-24 17:33:14,743][2364831] Updated weights for policy 0, policy_version 1308 (0.0011)
|
| 716 |
+
[2023-02-24 17:33:15,710][2364831] Updated weights for policy 0, policy_version 1318 (0.0012)
|
| 717 |
+
[2023-02-24 17:33:16,266][2364708] Fps is (10 sec: 41370.3, 60 sec: 40374.7, 300 sec: 40374.7). Total num frames: 5419008. Throughput: 0: 9385.3. Samples: 330789. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 718 |
+
[2023-02-24 17:33:16,266][2364708] Avg episode reward: [(0, '26.183')]
|
| 719 |
+
[2023-02-24 17:33:16,724][2364831] Updated weights for policy 0, policy_version 1328 (0.0008)
|
| 720 |
+
[2023-02-24 17:33:17,710][2364831] Updated weights for policy 0, policy_version 1338 (0.0014)
|
| 721 |
+
[2023-02-24 17:33:18,666][2364831] Updated weights for policy 0, policy_version 1348 (0.0009)
|
| 722 |
+
[2023-02-24 17:33:19,683][2364831] Updated weights for policy 0, policy_version 1358 (0.0009)
|
| 723 |
+
[2023-02-24 17:33:20,617][2364831] Updated weights for policy 0, policy_version 1368 (0.0010)
|
| 724 |
+
[2023-02-24 17:33:21,266][2364708] Fps is (10 sec: 41370.0, 60 sec: 40550.4, 300 sec: 40550.4). Total num frames: 5627904. Throughput: 0: 9770.6. Samples: 393129. Policy #0 lag: (min: 1.0, avg: 2.0, max: 4.0)
|
| 725 |
+
[2023-02-24 17:33:21,266][2364708] Avg episode reward: [(0, '25.398')]
|
| 726 |
+
[2023-02-24 17:33:21,637][2364831] Updated weights for policy 0, policy_version 1378 (0.0009)
|
| 727 |
+
[2023-02-24 17:33:22,601][2364831] Updated weights for policy 0, policy_version 1388 (0.0012)
|
| 728 |
+
[2023-02-24 17:33:23,610][2364831] Updated weights for policy 0, policy_version 1398 (0.0009)
|
| 729 |
+
[2023-02-24 17:33:24,587][2364831] Updated weights for policy 0, policy_version 1408 (0.0012)
|
| 730 |
+
[2023-02-24 17:33:25,585][2364831] Updated weights for policy 0, policy_version 1418 (0.0010)
|
| 731 |
+
[2023-02-24 17:33:26,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 40595.8, 300 sec: 40595.8). Total num frames: 5832704. Throughput: 0: 10069.7. Samples: 455439. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 732 |
+
[2023-02-24 17:33:26,266][2364708] Avg episode reward: [(0, '24.553')]
|
| 733 |
+
[2023-02-24 17:33:26,570][2364831] Updated weights for policy 0, policy_version 1428 (0.0009)
|
| 734 |
+
[2023-02-24 17:33:27,565][2364831] Updated weights for policy 0, policy_version 1438 (0.0009)
|
| 735 |
+
[2023-02-24 17:33:28,519][2364831] Updated weights for policy 0, policy_version 1448 (0.0012)
|
| 736 |
+
[2023-02-24 17:33:29,541][2364831] Updated weights for policy 0, policy_version 1458 (0.0011)
|
| 737 |
+
[2023-02-24 17:33:30,518][2364831] Updated weights for policy 0, policy_version 1468 (0.0012)
|
| 738 |
+
[2023-02-24 17:33:31,266][2364708] Fps is (10 sec: 41369.0, 60 sec: 40714.1, 300 sec: 40714.1). Total num frames: 6041600. Throughput: 0: 10387.5. Samples: 486495. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0)
|
| 739 |
+
[2023-02-24 17:33:31,266][2364708] Avg episode reward: [(0, '27.755')]
|
| 740 |
+
[2023-02-24 17:33:31,537][2364831] Updated weights for policy 0, policy_version 1478 (0.0009)
|
| 741 |
+
[2023-02-24 17:33:32,488][2364831] Updated weights for policy 0, policy_version 1488 (0.0009)
|
| 742 |
+
[2023-02-24 17:33:33,488][2364831] Updated weights for policy 0, policy_version 1498 (0.0010)
|
| 743 |
+
[2023-02-24 17:33:34,494][2364831] Updated weights for policy 0, policy_version 1508 (0.0009)
|
| 744 |
+
[2023-02-24 17:33:35,471][2364831] Updated weights for policy 0, policy_version 1518 (0.0012)
|
| 745 |
+
[2023-02-24 17:33:36,266][2364708] Fps is (10 sec: 41368.5, 60 sec: 40736.3, 300 sec: 40736.3). Total num frames: 6246400. Throughput: 0: 10367.1. Samples: 548559. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 746 |
+
[2023-02-24 17:33:36,267][2364708] Avg episode reward: [(0, '29.595')]
|
| 747 |
+
[2023-02-24 17:33:36,445][2364831] Updated weights for policy 0, policy_version 1528 (0.0015)
|
| 748 |
+
[2023-02-24 17:33:37,457][2364831] Updated weights for policy 0, policy_version 1538 (0.0010)
|
| 749 |
+
[2023-02-24 17:33:38,386][2364831] Updated weights for policy 0, policy_version 1548 (0.0010)
|
| 750 |
+
[2023-02-24 17:33:39,394][2364831] Updated weights for policy 0, policy_version 1558 (0.0009)
|
| 751 |
+
[2023-02-24 17:33:40,414][2364831] Updated weights for policy 0, policy_version 1568 (0.0013)
|
| 752 |
+
[2023-02-24 17:33:41,266][2364708] Fps is (10 sec: 41779.5, 60 sec: 40891.7, 300 sec: 40891.7). Total num frames: 6459392. Throughput: 0: 10363.3. Samples: 610929. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 753 |
+
[2023-02-24 17:33:41,266][2364708] Avg episode reward: [(0, '27.467')]
|
| 754 |
+
[2023-02-24 17:33:41,392][2364831] Updated weights for policy 0, policy_version 1578 (0.0011)
|
| 755 |
+
[2023-02-24 17:33:42,409][2364831] Updated weights for policy 0, policy_version 1588 (0.0015)
|
| 756 |
+
[2023-02-24 17:33:43,364][2364831] Updated weights for policy 0, policy_version 1598 (0.0016)
|
| 757 |
+
[2023-02-24 17:33:44,391][2364831] Updated weights for policy 0, policy_version 1608 (0.0009)
|
| 758 |
+
[2023-02-24 17:33:45,344][2364831] Updated weights for policy 0, policy_version 1618 (0.0009)
|
| 759 |
+
[2023-02-24 17:33:46,266][2364708] Fps is (10 sec: 41371.0, 60 sec: 41437.9, 300 sec: 40834.0). Total num frames: 6660096. Throughput: 0: 10362.0. Samples: 641805. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 760 |
+
[2023-02-24 17:33:46,266][2364708] Avg episode reward: [(0, '26.443')]
|
| 761 |
+
[2023-02-24 17:33:46,345][2364831] Updated weights for policy 0, policy_version 1628 (0.0009)
|
| 762 |
+
[2023-02-24 17:33:47,361][2364831] Updated weights for policy 0, policy_version 1638 (0.0012)
|
| 763 |
+
[2023-02-24 17:33:48,358][2364831] Updated weights for policy 0, policy_version 1648 (0.0015)
|
| 764 |
+
[2023-02-24 17:33:49,372][2364831] Updated weights for policy 0, policy_version 1658 (0.0010)
|
| 765 |
+
[2023-02-24 17:33:50,384][2364831] Updated weights for policy 0, policy_version 1668 (0.0009)
|
| 766 |
+
[2023-02-24 17:33:51,266][2364708] Fps is (10 sec: 40550.3, 60 sec: 41369.5, 300 sec: 40842.9). Total num frames: 6864896. Throughput: 0: 10346.7. Samples: 703164. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0)
|
| 767 |
+
[2023-02-24 17:33:51,266][2364708] Avg episode reward: [(0, '29.470')]
|
| 768 |
+
[2023-02-24 17:33:51,339][2364831] Updated weights for policy 0, policy_version 1678 (0.0009)
|
| 769 |
+
[2023-02-24 17:33:52,333][2364831] Updated weights for policy 0, policy_version 1688 (0.0013)
|
| 770 |
+
[2023-02-24 17:33:53,373][2364831] Updated weights for policy 0, policy_version 1698 (0.0010)
|
| 771 |
+
[2023-02-24 17:33:54,326][2364831] Updated weights for policy 0, policy_version 1708 (0.0011)
|
| 772 |
+
[2023-02-24 17:33:55,317][2364831] Updated weights for policy 0, policy_version 1718 (0.0015)
|
| 773 |
+
[2023-02-24 17:33:56,266][2364708] Fps is (10 sec: 41369.2, 60 sec: 41369.5, 300 sec: 40905.3). Total num frames: 7073792. Throughput: 0: 10341.1. Samples: 765279. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
|
| 774 |
+
[2023-02-24 17:33:56,266][2364708] Avg episode reward: [(0, '29.662')]
|
| 775 |
+
[2023-02-24 17:33:56,319][2364831] Updated weights for policy 0, policy_version 1728 (0.0009)
|
| 776 |
+
[2023-02-24 17:33:57,289][2364831] Updated weights for policy 0, policy_version 1738 (0.0014)
|
| 777 |
+
[2023-02-24 17:33:58,346][2364831] Updated weights for policy 0, policy_version 1748 (0.0009)
|
| 778 |
+
[2023-02-24 17:33:59,308][2364831] Updated weights for policy 0, policy_version 1758 (0.0009)
|
| 779 |
+
[2023-02-24 17:34:00,266][2364831] Updated weights for policy 0, policy_version 1768 (0.0009)
|
| 780 |
+
[2023-02-24 17:34:01,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41369.6, 300 sec: 40908.7). Total num frames: 7278592. Throughput: 0: 10343.3. Samples: 796236. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
|
| 781 |
+
[2023-02-24 17:34:01,266][2364708] Avg episode reward: [(0, '28.381')]
|
| 782 |
+
[2023-02-24 17:34:01,272][2364831] Updated weights for policy 0, policy_version 1778 (0.0014)
|
| 783 |
+
[2023-02-24 17:34:02,285][2364831] Updated weights for policy 0, policy_version 1788 (0.0012)
|
| 784 |
+
[2023-02-24 17:34:03,229][2364831] Updated weights for policy 0, policy_version 1798 (0.0014)
|
| 785 |
+
[2023-02-24 17:34:04,225][2364831] Updated weights for policy 0, policy_version 1808 (0.0011)
|
| 786 |
+
[2023-02-24 17:34:05,252][2364831] Updated weights for policy 0, policy_version 1818 (0.0011)
|
| 787 |
+
[2023-02-24 17:34:06,217][2364831] Updated weights for policy 0, policy_version 1828 (0.0014)
|
| 788 |
+
[2023-02-24 17:34:06,266][2364708] Fps is (10 sec: 41370.1, 60 sec: 41369.8, 300 sec: 40960.0). Total num frames: 7487488. Throughput: 0: 10333.9. Samples: 858156. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 789 |
+
[2023-02-24 17:34:06,266][2364708] Avg episode reward: [(0, '28.723')]
|
| 790 |
+
[2023-02-24 17:34:07,238][2364831] Updated weights for policy 0, policy_version 1838 (0.0012)
|
| 791 |
+
[2023-02-24 17:34:08,199][2364831] Updated weights for policy 0, policy_version 1848 (0.0009)
|
| 792 |
+
[2023-02-24 17:34:09,209][2364831] Updated weights for policy 0, policy_version 1858 (0.0015)
|
| 793 |
+
[2023-02-24 17:34:10,200][2364831] Updated weights for policy 0, policy_version 1868 (0.0013)
|
| 794 |
+
[2023-02-24 17:34:11,160][2364831] Updated weights for policy 0, policy_version 1878 (0.0012)
|
| 795 |
+
[2023-02-24 17:34:11,266][2364708] Fps is (10 sec: 41370.0, 60 sec: 41301.4, 300 sec: 40960.0). Total num frames: 7692288. Throughput: 0: 10328.4. Samples: 920217. Policy #0 lag: (min: 0.0, avg: 1.6, max: 3.0)
|
| 796 |
+
[2023-02-24 17:34:11,266][2364708] Avg episode reward: [(0, '27.028')]
|
| 797 |
+
[2023-02-24 17:34:12,189][2364831] Updated weights for policy 0, policy_version 1888 (0.0013)
|
| 798 |
+
[2023-02-24 17:34:13,157][2364831] Updated weights for policy 0, policy_version 1898 (0.0009)
|
| 799 |
+
[2023-02-24 17:34:14,140][2364831] Updated weights for policy 0, policy_version 1908 (0.0009)
|
| 800 |
+
[2023-02-24 17:34:15,142][2364831] Updated weights for policy 0, policy_version 1918 (0.0009)
|
| 801 |
+
[2023-02-24 17:34:16,149][2364831] Updated weights for policy 0, policy_version 1928 (0.0008)
|
| 802 |
+
[2023-02-24 17:34:16,266][2364708] Fps is (10 sec: 41368.9, 60 sec: 41369.6, 300 sec: 41003.1). Total num frames: 7901184. Throughput: 0: 10329.2. Samples: 951309. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 803 |
+
[2023-02-24 17:34:16,266][2364708] Avg episode reward: [(0, '31.603')]
|
| 804 |
+
[2023-02-24 17:34:16,267][2364791] Saving new best policy, reward=31.603!
|
| 805 |
+
[2023-02-24 17:34:17,141][2364831] Updated weights for policy 0, policy_version 1938 (0.0011)
|
| 806 |
+
[2023-02-24 17:34:18,125][2364831] Updated weights for policy 0, policy_version 1948 (0.0010)
|
| 807 |
+
[2023-02-24 17:34:19,131][2364831] Updated weights for policy 0, policy_version 1958 (0.0012)
|
| 808 |
+
[2023-02-24 17:34:20,142][2364831] Updated weights for policy 0, policy_version 1968 (0.0009)
|
| 809 |
+
[2023-02-24 17:34:21,131][2364831] Updated weights for policy 0, policy_version 1978 (0.0014)
|
| 810 |
+
[2023-02-24 17:34:21,266][2364708] Fps is (10 sec: 41369.1, 60 sec: 41301.3, 300 sec: 41000.9). Total num frames: 8105984. Throughput: 0: 10320.3. Samples: 1012971. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 811 |
+
[2023-02-24 17:34:21,266][2364708] Avg episode reward: [(0, '28.359')]
|
| 812 |
+
[2023-02-24 17:34:22,137][2364831] Updated weights for policy 0, policy_version 1988 (0.0009)
|
| 813 |
+
[2023-02-24 17:34:23,105][2364831] Updated weights for policy 0, policy_version 1998 (0.0009)
|
| 814 |
+
[2023-02-24 17:34:24,115][2364831] Updated weights for policy 0, policy_version 2008 (0.0012)
|
| 815 |
+
[2023-02-24 17:34:25,058][2364831] Updated weights for policy 0, policy_version 2018 (0.0010)
|
| 816 |
+
[2023-02-24 17:34:26,094][2364831] Updated weights for policy 0, policy_version 2028 (0.0010)
|
| 817 |
+
[2023-02-24 17:34:26,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41369.6, 300 sec: 41038.0). Total num frames: 8314880. Throughput: 0: 10310.5. Samples: 1074903. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 818 |
+
[2023-02-24 17:34:26,266][2364708] Avg episode reward: [(0, '28.710')]
|
| 819 |
+
[2023-02-24 17:34:27,060][2364831] Updated weights for policy 0, policy_version 2038 (0.0011)
|
| 820 |
+
[2023-02-24 17:34:28,047][2364831] Updated weights for policy 0, policy_version 2048 (0.0013)
|
| 821 |
+
[2023-02-24 17:34:29,023][2364831] Updated weights for policy 0, policy_version 2058 (0.0009)
|
| 822 |
+
[2023-02-24 17:34:30,021][2364831] Updated weights for policy 0, policy_version 2068 (0.0012)
|
| 823 |
+
[2023-02-24 17:34:31,055][2364831] Updated weights for policy 0, policy_version 2078 (0.0009)
|
| 824 |
+
[2023-02-24 17:34:31,266][2364708] Fps is (10 sec: 41369.6, 60 sec: 41301.4, 300 sec: 41034.4). Total num frames: 8519680. Throughput: 0: 10314.6. Samples: 1105962. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 825 |
+
[2023-02-24 17:34:31,266][2364708] Avg episode reward: [(0, '32.526')]
|
| 826 |
+
[2023-02-24 17:34:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000002080_8519680.pth...
|
| 827 |
+
[2023-02-24 17:34:31,337][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000759_3108864.pth
|
| 828 |
+
[2023-02-24 17:34:31,343][2364791] Saving new best policy, reward=32.526!
|
| 829 |
+
[2023-02-24 17:34:32,027][2364831] Updated weights for policy 0, policy_version 2088 (0.0014)
|
| 830 |
+
[2023-02-24 17:34:33,002][2364831] Updated weights for policy 0, policy_version 2098 (0.0011)
|
| 831 |
+
[2023-02-24 17:34:34,028][2364831] Updated weights for policy 0, policy_version 2108 (0.0010)
|
| 832 |
+
[2023-02-24 17:34:34,994][2364831] Updated weights for policy 0, policy_version 2118 (0.0009)
|
| 833 |
+
[2023-02-24 17:34:36,021][2364831] Updated weights for policy 0, policy_version 2128 (0.0011)
|
| 834 |
+
[2023-02-24 17:34:36,266][2364708] Fps is (10 sec: 40960.1, 60 sec: 41301.5, 300 sec: 41031.2). Total num frames: 8724480. Throughput: 0: 10328.4. Samples: 1167942. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 835 |
+
[2023-02-24 17:34:36,266][2364708] Avg episode reward: [(0, '29.338')]
|
| 836 |
+
[2023-02-24 17:34:37,019][2364831] Updated weights for policy 0, policy_version 2138 (0.0012)
|
| 837 |
+
[2023-02-24 17:34:38,029][2364831] Updated weights for policy 0, policy_version 2148 (0.0010)
|
| 838 |
+
[2023-02-24 17:34:38,999][2364831] Updated weights for policy 0, policy_version 2158 (0.0009)
|
| 839 |
+
[2023-02-24 17:34:40,008][2364831] Updated weights for policy 0, policy_version 2168 (0.0009)
|
| 840 |
+
[2023-02-24 17:34:40,960][2364831] Updated weights for policy 0, policy_version 2178 (0.0013)
|
| 841 |
+
[2023-02-24 17:34:41,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41164.8, 300 sec: 41028.2). Total num frames: 8929280. Throughput: 0: 10315.9. Samples: 1229496. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 842 |
+
[2023-02-24 17:34:41,266][2364708] Avg episode reward: [(0, '28.569')]
|
| 843 |
+
[2023-02-24 17:34:41,985][2364831] Updated weights for policy 0, policy_version 2188 (0.0012)
|
| 844 |
+
[2023-02-24 17:34:42,962][2364831] Updated weights for policy 0, policy_version 2198 (0.0009)
|
| 845 |
+
[2023-02-24 17:34:43,968][2364831] Updated weights for policy 0, policy_version 2208 (0.0009)
|
| 846 |
+
[2023-02-24 17:34:44,995][2364831] Updated weights for policy 0, policy_version 2218 (0.0010)
|
| 847 |
+
[2023-02-24 17:34:45,933][2364831] Updated weights for policy 0, policy_version 2228 (0.0010)
|
| 848 |
+
[2023-02-24 17:34:46,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41301.2, 300 sec: 41058.3). Total num frames: 9138176. Throughput: 0: 10313.9. Samples: 1260363. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 849 |
+
[2023-02-24 17:34:46,266][2364708] Avg episode reward: [(0, '29.705')]
|
| 850 |
+
[2023-02-24 17:34:46,949][2364831] Updated weights for policy 0, policy_version 2238 (0.0011)
|
| 851 |
+
[2023-02-24 17:34:47,940][2364831] Updated weights for policy 0, policy_version 2248 (0.0012)
|
| 852 |
+
[2023-02-24 17:34:48,931][2364831] Updated weights for policy 0, policy_version 2258 (0.0016)
|
| 853 |
+
[2023-02-24 17:34:49,903][2364831] Updated weights for policy 0, policy_version 2268 (0.0015)
|
| 854 |
+
[2023-02-24 17:34:50,883][2364831] Updated weights for policy 0, policy_version 2278 (0.0009)
|
| 855 |
+
[2023-02-24 17:34:51,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41301.4, 300 sec: 41054.5). Total num frames: 9342976. Throughput: 0: 10311.3. Samples: 1322166. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0)
|
| 856 |
+
[2023-02-24 17:34:51,266][2364708] Avg episode reward: [(0, '30.602')]
|
| 857 |
+
[2023-02-24 17:34:51,902][2364831] Updated weights for policy 0, policy_version 2288 (0.0010)
|
| 858 |
+
[2023-02-24 17:34:52,909][2364831] Updated weights for policy 0, policy_version 2298 (0.0010)
|
| 859 |
+
[2023-02-24 17:34:53,904][2364831] Updated weights for policy 0, policy_version 2308 (0.0010)
|
| 860 |
+
[2023-02-24 17:34:54,860][2364831] Updated weights for policy 0, policy_version 2318 (0.0010)
|
| 861 |
+
[2023-02-24 17:34:55,858][2364831] Updated weights for policy 0, policy_version 2328 (0.0009)
|
| 862 |
+
[2023-02-24 17:34:56,266][2364708] Fps is (10 sec: 40960.2, 60 sec: 41233.1, 300 sec: 41051.0). Total num frames: 9547776. Throughput: 0: 10311.1. Samples: 1384218. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 863 |
+
[2023-02-24 17:34:56,266][2364708] Avg episode reward: [(0, '29.322')]
|
| 864 |
+
[2023-02-24 17:34:56,865][2364831] Updated weights for policy 0, policy_version 2338 (0.0009)
|
| 865 |
+
[2023-02-24 17:34:57,857][2364831] Updated weights for policy 0, policy_version 2348 (0.0009)
|
| 866 |
+
[2023-02-24 17:34:58,810][2364831] Updated weights for policy 0, policy_version 2358 (0.0016)
|
| 867 |
+
[2023-02-24 17:34:59,854][2364831] Updated weights for policy 0, policy_version 2368 (0.0012)
|
| 868 |
+
[2023-02-24 17:35:00,835][2364831] Updated weights for policy 0, policy_version 2378 (0.0009)
|
| 869 |
+
[2023-02-24 17:35:01,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41301.3, 300 sec: 41077.0). Total num frames: 9756672. Throughput: 0: 10308.8. Samples: 1415205. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
|
| 870 |
+
[2023-02-24 17:35:01,266][2364708] Avg episode reward: [(0, '30.241')]
|
| 871 |
+
[2023-02-24 17:35:01,804][2364831] Updated weights for policy 0, policy_version 2388 (0.0012)
|
| 872 |
+
[2023-02-24 17:35:02,822][2364831] Updated weights for policy 0, policy_version 2398 (0.0010)
|
| 873 |
+
[2023-02-24 17:35:03,814][2364831] Updated weights for policy 0, policy_version 2408 (0.0010)
|
| 874 |
+
[2023-02-24 17:35:04,799][2364831] Updated weights for policy 0, policy_version 2418 (0.0011)
|
| 875 |
+
[2023-02-24 17:35:05,796][2364831] Updated weights for policy 0, policy_version 2428 (0.0009)
|
| 876 |
+
[2023-02-24 17:35:06,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41233.0, 300 sec: 41073.0). Total num frames: 9961472. Throughput: 0: 10314.6. Samples: 1477128. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0)
|
| 877 |
+
[2023-02-24 17:35:06,266][2364708] Avg episode reward: [(0, '26.511')]
|
| 878 |
+
[2023-02-24 17:35:06,791][2364831] Updated weights for policy 0, policy_version 2438 (0.0012)
|
| 879 |
+
[2023-02-24 17:35:07,790][2364831] Updated weights for policy 0, policy_version 2448 (0.0009)
|
| 880 |
+
[2023-02-24 17:35:08,780][2364831] Updated weights for policy 0, policy_version 2458 (0.0014)
|
| 881 |
+
[2023-02-24 17:35:09,752][2364831] Updated weights for policy 0, policy_version 2468 (0.0010)
|
| 882 |
+
[2023-02-24 17:35:10,772][2364831] Updated weights for policy 0, policy_version 2478 (0.0010)
|
| 883 |
+
[2023-02-24 17:35:11,266][2364708] Fps is (10 sec: 40958.9, 60 sec: 41232.8, 300 sec: 41069.1). Total num frames: 10166272. Throughput: 0: 10309.2. Samples: 1538820. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 884 |
+
[2023-02-24 17:35:11,267][2364708] Avg episode reward: [(0, '31.927')]
|
| 885 |
+
[2023-02-24 17:35:11,766][2364831] Updated weights for policy 0, policy_version 2488 (0.0012)
|
| 886 |
+
[2023-02-24 17:35:12,753][2364831] Updated weights for policy 0, policy_version 2498 (0.0011)
|
| 887 |
+
[2023-02-24 17:35:13,754][2364831] Updated weights for policy 0, policy_version 2508 (0.0014)
|
| 888 |
+
[2023-02-24 17:35:14,735][2364831] Updated weights for policy 0, policy_version 2518 (0.0013)
|
| 889 |
+
[2023-02-24 17:35:15,703][2364831] Updated weights for policy 0, policy_version 2528 (0.0011)
|
| 890 |
+
[2023-02-24 17:35:16,266][2364708] Fps is (10 sec: 41370.2, 60 sec: 41233.2, 300 sec: 41092.1). Total num frames: 10375168. Throughput: 0: 10308.7. Samples: 1569852. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 891 |
+
[2023-02-24 17:35:16,266][2364708] Avg episode reward: [(0, '29.333')]
|
| 892 |
+
[2023-02-24 17:35:16,713][2364831] Updated weights for policy 0, policy_version 2538 (0.0012)
|
| 893 |
+
[2023-02-24 17:35:17,728][2364831] Updated weights for policy 0, policy_version 2548 (0.0009)
|
| 894 |
+
[2023-02-24 17:35:18,681][2364831] Updated weights for policy 0, policy_version 2558 (0.0012)
|
| 895 |
+
[2023-02-24 17:35:19,719][2364831] Updated weights for policy 0, policy_version 2568 (0.0008)
|
| 896 |
+
[2023-02-24 17:35:20,725][2364831] Updated weights for policy 0, policy_version 2578 (0.0010)
|
| 897 |
+
[2023-02-24 17:35:21,266][2364708] Fps is (10 sec: 41370.6, 60 sec: 41233.1, 300 sec: 41088.0). Total num frames: 10579968. Throughput: 0: 10308.5. Samples: 1631826. Policy #0 lag: (min: 0.0, avg: 1.4, max: 3.0)
|
| 898 |
+
[2023-02-24 17:35:21,266][2364708] Avg episode reward: [(0, '29.221')]
|
| 899 |
+
[2023-02-24 17:35:21,646][2364831] Updated weights for policy 0, policy_version 2588 (0.0013)
|
| 900 |
+
[2023-02-24 17:35:22,678][2364831] Updated weights for policy 0, policy_version 2598 (0.0011)
|
| 901 |
+
[2023-02-24 17:35:23,706][2364831] Updated weights for policy 0, policy_version 2608 (0.0010)
|
| 902 |
+
[2023-02-24 17:35:24,640][2364831] Updated weights for policy 0, policy_version 2618 (0.0014)
|
| 903 |
+
[2023-02-24 17:35:25,686][2364831] Updated weights for policy 0, policy_version 2628 (0.0014)
|
| 904 |
+
[2023-02-24 17:35:26,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41233.2, 300 sec: 41108.9). Total num frames: 10788864. Throughput: 0: 10318.8. Samples: 1693842. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
|
| 905 |
+
[2023-02-24 17:35:26,266][2364708] Avg episode reward: [(0, '32.770')]
|
| 906 |
+
[2023-02-24 17:35:26,267][2364791] Saving new best policy, reward=32.770!
|
| 907 |
+
[2023-02-24 17:35:26,645][2364831] Updated weights for policy 0, policy_version 2638 (0.0019)
|
| 908 |
+
[2023-02-24 17:35:27,596][2364831] Updated weights for policy 0, policy_version 2648 (0.0012)
|
| 909 |
+
[2023-02-24 17:35:28,675][2364831] Updated weights for policy 0, policy_version 2658 (0.0012)
|
| 910 |
+
[2023-02-24 17:35:29,615][2364831] Updated weights for policy 0, policy_version 2668 (0.0009)
|
| 911 |
+
[2023-02-24 17:35:30,625][2364831] Updated weights for policy 0, policy_version 2678 (0.0012)
|
| 912 |
+
[2023-02-24 17:35:31,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41233.0, 300 sec: 41104.5). Total num frames: 10993664. Throughput: 0: 10317.5. Samples: 1724652. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 913 |
+
[2023-02-24 17:35:31,266][2364708] Avg episode reward: [(0, '33.019')]
|
| 914 |
+
[2023-02-24 17:35:31,271][2364791] Saving new best policy, reward=33.019!
|
| 915 |
+
[2023-02-24 17:35:31,627][2364831] Updated weights for policy 0, policy_version 2688 (0.0013)
|
| 916 |
+
[2023-02-24 17:35:32,607][2364831] Updated weights for policy 0, policy_version 2698 (0.0012)
|
| 917 |
+
[2023-02-24 17:35:33,625][2364831] Updated weights for policy 0, policy_version 2708 (0.0009)
|
| 918 |
+
[2023-02-24 17:35:34,595][2364831] Updated weights for policy 0, policy_version 2718 (0.0010)
|
| 919 |
+
[2023-02-24 17:35:35,612][2364831] Updated weights for policy 0, policy_version 2728 (0.0010)
|
| 920 |
+
[2023-02-24 17:35:36,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41233.1, 300 sec: 41100.4). Total num frames: 11198464. Throughput: 0: 10313.8. Samples: 1786287. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
|
| 921 |
+
[2023-02-24 17:35:36,266][2364708] Avg episode reward: [(0, '30.687')]
|
| 922 |
+
[2023-02-24 17:35:36,597][2364831] Updated weights for policy 0, policy_version 2738 (0.0012)
|
| 923 |
+
[2023-02-24 17:35:37,588][2364831] Updated weights for policy 0, policy_version 2748 (0.0012)
|
| 924 |
+
[2023-02-24 17:35:38,625][2364831] Updated weights for policy 0, policy_version 2758 (0.0016)
|
| 925 |
+
[2023-02-24 17:35:39,609][2364831] Updated weights for policy 0, policy_version 2768 (0.0009)
|
| 926 |
+
[2023-02-24 17:35:40,592][2364831] Updated weights for policy 0, policy_version 2778 (0.0009)
|
| 927 |
+
[2023-02-24 17:35:41,266][2364708] Fps is (10 sec: 40960.2, 60 sec: 41233.0, 300 sec: 41096.5). Total num frames: 11403264. Throughput: 0: 10304.3. Samples: 1847913. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 928 |
+
[2023-02-24 17:35:41,266][2364708] Avg episode reward: [(0, '30.382')]
|
| 929 |
+
[2023-02-24 17:35:41,573][2364831] Updated weights for policy 0, policy_version 2788 (0.0012)
|
| 930 |
+
[2023-02-24 17:35:42,590][2364831] Updated weights for policy 0, policy_version 2798 (0.0010)
|
| 931 |
+
[2023-02-24 17:35:43,575][2364831] Updated weights for policy 0, policy_version 2808 (0.0010)
|
| 932 |
+
[2023-02-24 17:35:44,572][2364831] Updated weights for policy 0, policy_version 2818 (0.0011)
|
| 933 |
+
[2023-02-24 17:35:45,597][2364831] Updated weights for policy 0, policy_version 2828 (0.0008)
|
| 934 |
+
[2023-02-24 17:35:46,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 41233.1, 300 sec: 41115.0). Total num frames: 11612160. Throughput: 0: 10300.4. Samples: 1878723. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0)
|
| 935 |
+
[2023-02-24 17:35:46,266][2364708] Avg episode reward: [(0, '30.394')]
|
| 936 |
+
[2023-02-24 17:35:46,560][2364831] Updated weights for policy 0, policy_version 2838 (0.0010)
|
| 937 |
+
[2023-02-24 17:35:47,531][2364831] Updated weights for policy 0, policy_version 2848 (0.0010)
|
| 938 |
+
[2023-02-24 17:35:48,545][2364831] Updated weights for policy 0, policy_version 2858 (0.0012)
|
| 939 |
+
[2023-02-24 17:35:49,500][2364831] Updated weights for policy 0, policy_version 2868 (0.0010)
|
| 940 |
+
[2023-02-24 17:35:50,524][2364831] Updated weights for policy 0, policy_version 2878 (0.0012)
|
| 941 |
+
[2023-02-24 17:35:51,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41233.0, 300 sec: 41110.9). Total num frames: 11816960. Throughput: 0: 10303.3. Samples: 1940775. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 942 |
+
[2023-02-24 17:35:51,266][2364708] Avg episode reward: [(0, '27.697')]
|
| 943 |
+
[2023-02-24 17:35:51,481][2364831] Updated weights for policy 0, policy_version 2888 (0.0011)
|
| 944 |
+
[2023-02-24 17:35:52,493][2364831] Updated weights for policy 0, policy_version 2898 (0.0012)
|
| 945 |
+
[2023-02-24 17:35:53,490][2364831] Updated weights for policy 0, policy_version 2908 (0.0009)
|
| 946 |
+
[2023-02-24 17:35:54,455][2364831] Updated weights for policy 0, policy_version 2918 (0.0012)
|
| 947 |
+
[2023-02-24 17:35:55,469][2364831] Updated weights for policy 0, policy_version 2928 (0.0012)
|
| 948 |
+
[2023-02-24 17:35:56,266][2364708] Fps is (10 sec: 40960.4, 60 sec: 41233.1, 300 sec: 41107.0). Total num frames: 12021760. Throughput: 0: 10309.2. Samples: 2002731. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 949 |
+
[2023-02-24 17:35:56,266][2364708] Avg episode reward: [(0, '32.058')]
|
| 950 |
+
[2023-02-24 17:35:56,472][2364831] Updated weights for policy 0, policy_version 2938 (0.0009)
|
| 951 |
+
[2023-02-24 17:35:57,467][2364831] Updated weights for policy 0, policy_version 2948 (0.0011)
|
| 952 |
+
[2023-02-24 17:35:58,438][2364831] Updated weights for policy 0, policy_version 2958 (0.0013)
|
| 953 |
+
[2023-02-24 17:35:59,455][2364831] Updated weights for policy 0, policy_version 2968 (0.0009)
|
| 954 |
+
[2023-02-24 17:36:00,457][2364831] Updated weights for policy 0, policy_version 2978 (0.0009)
|
| 955 |
+
[2023-02-24 17:36:01,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41233.0, 300 sec: 41123.8). Total num frames: 12230656. Throughput: 0: 10305.4. Samples: 2033598. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 956 |
+
[2023-02-24 17:36:01,266][2364708] Avg episode reward: [(0, '29.736')]
|
| 957 |
+
[2023-02-24 17:36:01,465][2364831] Updated weights for policy 0, policy_version 2988 (0.0009)
|
| 958 |
+
[2023-02-24 17:36:02,473][2364831] Updated weights for policy 0, policy_version 2998 (0.0009)
|
| 959 |
+
[2023-02-24 17:36:03,476][2364831] Updated weights for policy 0, policy_version 3008 (0.0010)
|
| 960 |
+
[2023-02-24 17:36:04,459][2364831] Updated weights for policy 0, policy_version 3018 (0.0009)
|
| 961 |
+
[2023-02-24 17:36:05,480][2364831] Updated weights for policy 0, policy_version 3028 (0.0011)
|
| 962 |
+
[2023-02-24 17:36:06,266][2364708] Fps is (10 sec: 41369.1, 60 sec: 41233.0, 300 sec: 41119.8). Total num frames: 12435456. Throughput: 0: 10293.7. Samples: 2095044. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 963 |
+
[2023-02-24 17:36:06,266][2364708] Avg episode reward: [(0, '30.393')]
|
| 964 |
+
[2023-02-24 17:36:06,445][2364831] Updated weights for policy 0, policy_version 3038 (0.0012)
|
| 965 |
+
[2023-02-24 17:36:07,421][2364831] Updated weights for policy 0, policy_version 3048 (0.0009)
|
| 966 |
+
[2023-02-24 17:36:08,415][2364831] Updated weights for policy 0, policy_version 3058 (0.0011)
|
| 967 |
+
[2023-02-24 17:36:09,436][2364831] Updated weights for policy 0, policy_version 3068 (0.0010)
|
| 968 |
+
[2023-02-24 17:36:10,457][2364831] Updated weights for policy 0, policy_version 3078 (0.0009)
|
| 969 |
+
[2023-02-24 17:36:11,266][2364708] Fps is (10 sec: 40960.7, 60 sec: 41233.3, 300 sec: 41116.0). Total num frames: 12640256. Throughput: 0: 10281.7. Samples: 2156517. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 970 |
+
[2023-02-24 17:36:11,266][2364708] Avg episode reward: [(0, '30.391')]
|
| 971 |
+
[2023-02-24 17:36:11,465][2364831] Updated weights for policy 0, policy_version 3088 (0.0009)
|
| 972 |
+
[2023-02-24 17:36:12,457][2364831] Updated weights for policy 0, policy_version 3098 (0.0011)
|
| 973 |
+
[2023-02-24 17:36:13,406][2364831] Updated weights for policy 0, policy_version 3108 (0.0013)
|
| 974 |
+
[2023-02-24 17:36:14,404][2364831] Updated weights for policy 0, policy_version 3118 (0.0012)
|
| 975 |
+
[2023-02-24 17:36:15,425][2364831] Updated weights for policy 0, policy_version 3128 (0.0011)
|
| 976 |
+
[2023-02-24 17:36:16,266][2364708] Fps is (10 sec: 40960.3, 60 sec: 41164.7, 300 sec: 41112.4). Total num frames: 12845056. Throughput: 0: 10287.8. Samples: 2187600. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 977 |
+
[2023-02-24 17:36:16,266][2364708] Avg episode reward: [(0, '27.913')]
|
| 978 |
+
[2023-02-24 17:36:16,372][2364831] Updated weights for policy 0, policy_version 3138 (0.0014)
|
| 979 |
+
[2023-02-24 17:36:17,447][2364831] Updated weights for policy 0, policy_version 3148 (0.0009)
|
| 980 |
+
[2023-02-24 17:36:18,429][2364831] Updated weights for policy 0, policy_version 3158 (0.0009)
|
| 981 |
+
[2023-02-24 17:36:19,407][2364831] Updated weights for policy 0, policy_version 3168 (0.0013)
|
| 982 |
+
[2023-02-24 17:36:20,357][2364831] Updated weights for policy 0, policy_version 3178 (0.0009)
|
| 983 |
+
[2023-02-24 17:36:21,266][2364708] Fps is (10 sec: 40959.6, 60 sec: 41164.8, 300 sec: 41108.9). Total num frames: 13049856. Throughput: 0: 10288.8. Samples: 2249286. Policy #0 lag: (min: 0.0, avg: 1.9, max: 3.0)
|
| 984 |
+
[2023-02-24 17:36:21,266][2364708] Avg episode reward: [(0, '32.921')]
|
| 985 |
+
[2023-02-24 17:36:21,375][2364831] Updated weights for policy 0, policy_version 3188 (0.0012)
|
| 986 |
+
[2023-02-24 17:36:22,374][2364831] Updated weights for policy 0, policy_version 3198 (0.0015)
|
| 987 |
+
[2023-02-24 17:36:23,132][2364791] Signal inference workers to stop experience collection... (50 times)
|
| 988 |
+
[2023-02-24 17:36:23,134][2364791] Signal inference workers to resume experience collection... (50 times)
|
| 989 |
+
[2023-02-24 17:36:23,142][2364831] InferenceWorker_p0-w0: stopping experience collection (50 times)
|
| 990 |
+
[2023-02-24 17:36:23,145][2364831] InferenceWorker_p0-w0: resuming experience collection (50 times)
|
| 991 |
+
[2023-02-24 17:36:23,415][2364831] Updated weights for policy 0, policy_version 3208 (0.0010)
|
| 992 |
+
[2023-02-24 17:36:24,357][2364831] Updated weights for policy 0, policy_version 3218 (0.0009)
|
| 993 |
+
[2023-02-24 17:36:25,363][2364831] Updated weights for policy 0, policy_version 3228 (0.0014)
|
| 994 |
+
[2023-02-24 17:36:26,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41164.7, 300 sec: 41123.8). Total num frames: 13258752. Throughput: 0: 10290.0. Samples: 2310963. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 995 |
+
[2023-02-24 17:36:26,266][2364708] Avg episode reward: [(0, '34.018')]
|
| 996 |
+
[2023-02-24 17:36:26,267][2364791] Saving new best policy, reward=34.018!
|
| 997 |
+
[2023-02-24 17:36:26,376][2364831] Updated weights for policy 0, policy_version 3238 (0.0009)
|
| 998 |
+
[2023-02-24 17:36:27,385][2364831] Updated weights for policy 0, policy_version 3248 (0.0012)
|
| 999 |
+
[2023-02-24 17:36:28,374][2364831] Updated weights for policy 0, policy_version 3258 (0.0008)
|
| 1000 |
+
[2023-02-24 17:36:29,381][2364831] Updated weights for policy 0, policy_version 3268 (0.0009)
|
| 1001 |
+
[2023-02-24 17:36:30,372][2364831] Updated weights for policy 0, policy_version 3278 (0.0009)
|
| 1002 |
+
[2023-02-24 17:36:31,266][2364708] Fps is (10 sec: 41369.5, 60 sec: 41164.8, 300 sec: 41120.3). Total num frames: 13463552. Throughput: 0: 10287.8. Samples: 2341674. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 1003 |
+
[2023-02-24 17:36:31,266][2364708] Avg episode reward: [(0, '31.155')]
|
| 1004 |
+
[2023-02-24 17:36:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000003287_13463552.pth...
|
| 1005 |
+
[2023-02-24 17:36:31,331][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
|
| 1006 |
+
[2023-02-24 17:36:31,376][2364831] Updated weights for policy 0, policy_version 3288 (0.0010)
|
| 1007 |
+
[2023-02-24 17:36:32,389][2364831] Updated weights for policy 0, policy_version 3298 (0.0012)
|
| 1008 |
+
[2023-02-24 17:36:33,398][2364831] Updated weights for policy 0, policy_version 3308 (0.0013)
|
| 1009 |
+
[2023-02-24 17:36:34,328][2364831] Updated weights for policy 0, policy_version 3318 (0.0009)
|
| 1010 |
+
[2023-02-24 17:36:35,370][2364831] Updated weights for policy 0, policy_version 3328 (0.0009)
|
| 1011 |
+
[2023-02-24 17:36:36,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41164.8, 300 sec: 41116.9). Total num frames: 13668352. Throughput: 0: 10277.8. Samples: 2403273. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 1012 |
+
[2023-02-24 17:36:36,266][2364708] Avg episode reward: [(0, '32.249')]
|
| 1013 |
+
[2023-02-24 17:36:36,352][2364831] Updated weights for policy 0, policy_version 3338 (0.0008)
|
| 1014 |
+
[2023-02-24 17:36:37,358][2364831] Updated weights for policy 0, policy_version 3348 (0.0012)
|
| 1015 |
+
[2023-02-24 17:36:38,366][2364831] Updated weights for policy 0, policy_version 3358 (0.0013)
|
| 1016 |
+
[2023-02-24 17:36:39,348][2364831] Updated weights for policy 0, policy_version 3368 (0.0010)
|
| 1017 |
+
[2023-02-24 17:36:40,325][2364831] Updated weights for policy 0, policy_version 3378 (0.0009)
|
| 1018 |
+
[2023-02-24 17:36:41,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41164.9, 300 sec: 41113.6). Total num frames: 13873152. Throughput: 0: 10271.1. Samples: 2464929. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1019 |
+
[2023-02-24 17:36:41,266][2364708] Avg episode reward: [(0, '30.922')]
|
| 1020 |
+
[2023-02-24 17:36:41,354][2364831] Updated weights for policy 0, policy_version 3388 (0.0013)
|
| 1021 |
+
[2023-02-24 17:36:42,336][2364831] Updated weights for policy 0, policy_version 3398 (0.0011)
|
| 1022 |
+
[2023-02-24 17:36:43,307][2364831] Updated weights for policy 0, policy_version 3408 (0.0010)
|
| 1023 |
+
[2023-02-24 17:36:44,352][2364831] Updated weights for policy 0, policy_version 3418 (0.0017)
|
| 1024 |
+
[2023-02-24 17:36:45,308][2364831] Updated weights for policy 0, policy_version 3428 (0.0011)
|
| 1025 |
+
[2023-02-24 17:36:46,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.6, 300 sec: 41110.5). Total num frames: 14077952. Throughput: 0: 10271.3. Samples: 2495805. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 1026 |
+
[2023-02-24 17:36:46,266][2364708] Avg episode reward: [(0, '35.645')]
|
| 1027 |
+
[2023-02-24 17:36:46,267][2364791] Saving new best policy, reward=35.645!
|
| 1028 |
+
[2023-02-24 17:36:46,360][2364831] Updated weights for policy 0, policy_version 3438 (0.0011)
|
| 1029 |
+
[2023-02-24 17:36:47,341][2364831] Updated weights for policy 0, policy_version 3448 (0.0010)
|
| 1030 |
+
[2023-02-24 17:36:48,315][2364831] Updated weights for policy 0, policy_version 3458 (0.0012)
|
| 1031 |
+
[2023-02-24 17:36:49,289][2364831] Updated weights for policy 0, policy_version 3468 (0.0008)
|
| 1032 |
+
[2023-02-24 17:36:50,307][2364831] Updated weights for policy 0, policy_version 3478 (0.0009)
|
| 1033 |
+
[2023-02-24 17:36:51,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.6, 300 sec: 41107.5). Total num frames: 14282752. Throughput: 0: 10276.8. Samples: 2557500. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 1034 |
+
[2023-02-24 17:36:51,266][2364708] Avg episode reward: [(0, '34.180')]
|
| 1035 |
+
[2023-02-24 17:36:51,296][2364831] Updated weights for policy 0, policy_version 3488 (0.0009)
|
| 1036 |
+
[2023-02-24 17:36:52,295][2364831] Updated weights for policy 0, policy_version 3498 (0.0014)
|
| 1037 |
+
[2023-02-24 17:36:53,320][2364831] Updated weights for policy 0, policy_version 3508 (0.0010)
|
| 1038 |
+
[2023-02-24 17:36:54,312][2364831] Updated weights for policy 0, policy_version 3518 (0.0013)
|
| 1039 |
+
[2023-02-24 17:36:55,310][2364831] Updated weights for policy 0, policy_version 3528 (0.0012)
|
| 1040 |
+
[2023-02-24 17:36:56,260][2364831] Updated weights for policy 0, policy_version 3538 (0.0011)
|
| 1041 |
+
[2023-02-24 17:36:56,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41164.9, 300 sec: 41120.6). Total num frames: 14491648. Throughput: 0: 10279.0. Samples: 2619072. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0)
|
| 1042 |
+
[2023-02-24 17:36:56,266][2364708] Avg episode reward: [(0, '35.711')]
|
| 1043 |
+
[2023-02-24 17:36:56,267][2364791] Saving new best policy, reward=35.711!
|
| 1044 |
+
[2023-02-24 17:36:57,297][2364831] Updated weights for policy 0, policy_version 3548 (0.0014)
|
| 1045 |
+
[2023-02-24 17:36:58,305][2364831] Updated weights for policy 0, policy_version 3558 (0.0009)
|
| 1046 |
+
[2023-02-24 17:36:59,282][2364831] Updated weights for policy 0, policy_version 3568 (0.0009)
|
| 1047 |
+
[2023-02-24 17:37:00,281][2364831] Updated weights for policy 0, policy_version 3578 (0.0018)
|
| 1048 |
+
[2023-02-24 17:37:01,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.4, 300 sec: 41101.8). Total num frames: 14692352. Throughput: 0: 10270.1. Samples: 2649753. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1049 |
+
[2023-02-24 17:37:01,266][2364708] Avg episode reward: [(0, '32.713')]
|
| 1050 |
+
[2023-02-24 17:37:01,290][2364831] Updated weights for policy 0, policy_version 3588 (0.0011)
|
| 1051 |
+
[2023-02-24 17:37:02,293][2364831] Updated weights for policy 0, policy_version 3598 (0.0012)
|
| 1052 |
+
[2023-02-24 17:37:03,300][2364831] Updated weights for policy 0, policy_version 3608 (0.0010)
|
| 1053 |
+
[2023-02-24 17:37:04,288][2364831] Updated weights for policy 0, policy_version 3618 (0.0012)
|
| 1054 |
+
[2023-02-24 17:37:05,307][2364831] Updated weights for policy 0, policy_version 3628 (0.0012)
|
| 1055 |
+
[2023-02-24 17:37:06,256][2364831] Updated weights for policy 0, policy_version 3638 (0.0011)
|
| 1056 |
+
[2023-02-24 17:37:06,266][2364708] Fps is (10 sec: 40959.4, 60 sec: 41096.6, 300 sec: 41114.5). Total num frames: 14901248. Throughput: 0: 10265.3. Samples: 2711226. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1057 |
+
[2023-02-24 17:37:06,266][2364708] Avg episode reward: [(0, '33.770')]
|
| 1058 |
+
[2023-02-24 17:37:07,256][2364831] Updated weights for policy 0, policy_version 3648 (0.0010)
|
| 1059 |
+
[2023-02-24 17:37:08,283][2364831] Updated weights for policy 0, policy_version 3658 (0.0010)
|
| 1060 |
+
[2023-02-24 17:37:09,271][2364831] Updated weights for policy 0, policy_version 3668 (0.0010)
|
| 1061 |
+
[2023-02-24 17:37:10,247][2364831] Updated weights for policy 0, policy_version 3678 (0.0011)
|
| 1062 |
+
[2023-02-24 17:37:11,255][2364831] Updated weights for policy 0, policy_version 3688 (0.0009)
|
| 1063 |
+
[2023-02-24 17:37:11,266][2364708] Fps is (10 sec: 41369.7, 60 sec: 41096.5, 300 sec: 41111.7). Total num frames: 15106048. Throughput: 0: 10267.2. Samples: 2772984. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0)
|
| 1064 |
+
[2023-02-24 17:37:11,266][2364708] Avg episode reward: [(0, '35.557')]
|
| 1065 |
+
[2023-02-24 17:37:12,240][2364831] Updated weights for policy 0, policy_version 3698 (0.0010)
|
| 1066 |
+
[2023-02-24 17:37:13,251][2364831] Updated weights for policy 0, policy_version 3708 (0.0010)
|
| 1067 |
+
[2023-02-24 17:37:14,229][2364831] Updated weights for policy 0, policy_version 3718 (0.0009)
|
| 1068 |
+
[2023-02-24 17:37:15,279][2364831] Updated weights for policy 0, policy_version 3728 (0.0015)
|
| 1069 |
+
[2023-02-24 17:37:16,243][2364831] Updated weights for policy 0, policy_version 3738 (0.0011)
|
| 1070 |
+
[2023-02-24 17:37:16,266][2364708] Fps is (10 sec: 40960.5, 60 sec: 41096.6, 300 sec: 41108.9). Total num frames: 15310848. Throughput: 0: 10269.1. Samples: 2803782. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0)
|
| 1071 |
+
[2023-02-24 17:37:16,266][2364708] Avg episode reward: [(0, '34.978')]
|
| 1072 |
+
[2023-02-24 17:37:17,232][2364831] Updated weights for policy 0, policy_version 3748 (0.0011)
|
| 1073 |
+
[2023-02-24 17:37:18,232][2364831] Updated weights for policy 0, policy_version 3758 (0.0012)
|
| 1074 |
+
[2023-02-24 17:37:19,246][2364831] Updated weights for policy 0, policy_version 3768 (0.0011)
|
| 1075 |
+
[2023-02-24 17:37:20,215][2364831] Updated weights for policy 0, policy_version 3778 (0.0016)
|
| 1076 |
+
[2023-02-24 17:37:21,224][2364831] Updated weights for policy 0, policy_version 3788 (0.0009)
|
| 1077 |
+
[2023-02-24 17:37:21,266][2364708] Fps is (10 sec: 40959.6, 60 sec: 41096.5, 300 sec: 41106.3). Total num frames: 15515648. Throughput: 0: 10267.2. Samples: 2865300. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 1078 |
+
[2023-02-24 17:37:21,266][2364708] Avg episode reward: [(0, '32.422')]
|
| 1079 |
+
[2023-02-24 17:37:22,190][2364831] Updated weights for policy 0, policy_version 3798 (0.0009)
|
| 1080 |
+
[2023-02-24 17:37:23,210][2364831] Updated weights for policy 0, policy_version 3808 (0.0010)
|
| 1081 |
+
[2023-02-24 17:37:24,201][2364831] Updated weights for policy 0, policy_version 3818 (0.0009)
|
| 1082 |
+
[2023-02-24 17:37:25,224][2364831] Updated weights for policy 0, policy_version 3828 (0.0012)
|
| 1083 |
+
[2023-02-24 17:37:26,251][2364831] Updated weights for policy 0, policy_version 3838 (0.0012)
|
| 1084 |
+
[2023-02-24 17:37:26,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.4, 300 sec: 41103.7). Total num frames: 15720448. Throughput: 0: 10264.2. Samples: 2926818. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1085 |
+
[2023-02-24 17:37:26,266][2364708] Avg episode reward: [(0, '30.861')]
|
| 1086 |
+
[2023-02-24 17:37:27,226][2364831] Updated weights for policy 0, policy_version 3848 (0.0014)
|
| 1087 |
+
[2023-02-24 17:37:28,214][2364831] Updated weights for policy 0, policy_version 3858 (0.0010)
|
| 1088 |
+
[2023-02-24 17:37:29,243][2364831] Updated weights for policy 0, policy_version 3868 (0.0013)
|
| 1089 |
+
[2023-02-24 17:37:30,235][2364831] Updated weights for policy 0, policy_version 3878 (0.0009)
|
| 1090 |
+
[2023-02-24 17:37:31,194][2364831] Updated weights for policy 0, policy_version 3888 (0.0010)
|
| 1091 |
+
[2023-02-24 17:37:31,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41028.3, 300 sec: 41101.2). Total num frames: 15925248. Throughput: 0: 10260.7. Samples: 2957538. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1092 |
+
[2023-02-24 17:37:31,266][2364708] Avg episode reward: [(0, '33.478')]
|
| 1093 |
+
[2023-02-24 17:37:32,210][2364831] Updated weights for policy 0, policy_version 3898 (0.0011)
|
| 1094 |
+
[2023-02-24 17:37:33,187][2364831] Updated weights for policy 0, policy_version 3908 (0.0013)
|
| 1095 |
+
[2023-02-24 17:37:34,160][2364831] Updated weights for policy 0, policy_version 3918 (0.0012)
|
| 1096 |
+
[2023-02-24 17:37:35,197][2364831] Updated weights for policy 0, policy_version 3928 (0.0012)
|
| 1097 |
+
[2023-02-24 17:37:36,189][2364831] Updated weights for policy 0, policy_version 3938 (0.0012)
|
| 1098 |
+
[2023-02-24 17:37:36,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.3, 300 sec: 41098.8). Total num frames: 16130048. Throughput: 0: 10267.2. Samples: 3019524. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
|
| 1099 |
+
[2023-02-24 17:37:36,266][2364708] Avg episode reward: [(0, '34.030')]
|
| 1100 |
+
[2023-02-24 17:37:37,168][2364831] Updated weights for policy 0, policy_version 3948 (0.0010)
|
| 1101 |
+
[2023-02-24 17:37:38,212][2364831] Updated weights for policy 0, policy_version 3958 (0.0010)
|
| 1102 |
+
[2023-02-24 17:37:39,181][2364831] Updated weights for policy 0, policy_version 3968 (0.0009)
|
| 1103 |
+
[2023-02-24 17:37:40,158][2364831] Updated weights for policy 0, policy_version 3978 (0.0012)
|
| 1104 |
+
[2023-02-24 17:37:41,178][2364831] Updated weights for policy 0, policy_version 3988 (0.0011)
|
| 1105 |
+
[2023-02-24 17:37:41,266][2364708] Fps is (10 sec: 40960.6, 60 sec: 41028.3, 300 sec: 41223.8). Total num frames: 16334848. Throughput: 0: 10262.3. Samples: 3080874. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 1106 |
+
[2023-02-24 17:37:41,266][2364708] Avg episode reward: [(0, '30.119')]
|
| 1107 |
+
[2023-02-24 17:37:42,173][2364831] Updated weights for policy 0, policy_version 3998 (0.0009)
|
| 1108 |
+
[2023-02-24 17:37:43,173][2364831] Updated weights for policy 0, policy_version 4008 (0.0012)
|
| 1109 |
+
[2023-02-24 17:37:44,204][2364831] Updated weights for policy 0, policy_version 4018 (0.0013)
|
| 1110 |
+
[2023-02-24 17:37:45,182][2364831] Updated weights for policy 0, policy_version 4028 (0.0015)
|
| 1111 |
+
[2023-02-24 17:37:46,192][2364831] Updated weights for policy 0, policy_version 4038 (0.0010)
|
| 1112 |
+
[2023-02-24 17:37:46,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41028.2, 300 sec: 41209.9). Total num frames: 16539648. Throughput: 0: 10264.2. Samples: 3111642. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 1113 |
+
[2023-02-24 17:37:46,266][2364708] Avg episode reward: [(0, '34.674')]
|
| 1114 |
+
[2023-02-24 17:37:47,165][2364831] Updated weights for policy 0, policy_version 4048 (0.0009)
|
| 1115 |
+
[2023-02-24 17:37:48,150][2364831] Updated weights for policy 0, policy_version 4058 (0.0009)
|
| 1116 |
+
[2023-02-24 17:37:49,155][2364831] Updated weights for policy 0, policy_version 4068 (0.0010)
|
| 1117 |
+
[2023-02-24 17:37:50,176][2364831] Updated weights for policy 0, policy_version 4078 (0.0011)
|
| 1118 |
+
[2023-02-24 17:37:51,128][2364831] Updated weights for policy 0, policy_version 4088 (0.0013)
|
| 1119 |
+
[2023-02-24 17:37:51,266][2364708] Fps is (10 sec: 41369.0, 60 sec: 41096.4, 300 sec: 41209.9). Total num frames: 16748544. Throughput: 0: 10268.4. Samples: 3173304. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 1120 |
+
[2023-02-24 17:37:51,267][2364708] Avg episode reward: [(0, '33.236')]
|
| 1121 |
+
[2023-02-24 17:37:52,111][2364831] Updated weights for policy 0, policy_version 4098 (0.0009)
|
| 1122 |
+
[2023-02-24 17:37:53,146][2364831] Updated weights for policy 0, policy_version 4108 (0.0014)
|
| 1123 |
+
[2023-02-24 17:37:54,142][2364831] Updated weights for policy 0, policy_version 4118 (0.0012)
|
| 1124 |
+
[2023-02-24 17:37:55,117][2364831] Updated weights for policy 0, policy_version 4128 (0.0010)
|
| 1125 |
+
[2023-02-24 17:37:56,172][2364831] Updated weights for policy 0, policy_version 4138 (0.0011)
|
| 1126 |
+
[2023-02-24 17:37:56,266][2364708] Fps is (10 sec: 41369.4, 60 sec: 41028.2, 300 sec: 41209.9). Total num frames: 16953344. Throughput: 0: 10265.4. Samples: 3234927. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 1127 |
+
[2023-02-24 17:37:56,266][2364708] Avg episode reward: [(0, '33.288')]
|
| 1128 |
+
[2023-02-24 17:37:57,176][2364831] Updated weights for policy 0, policy_version 4148 (0.0009)
|
| 1129 |
+
[2023-02-24 17:37:58,108][2364831] Updated weights for policy 0, policy_version 4158 (0.0010)
|
| 1130 |
+
[2023-02-24 17:37:59,170][2364831] Updated weights for policy 0, policy_version 4168 (0.0016)
|
| 1131 |
+
[2023-02-24 17:38:00,167][2364831] Updated weights for policy 0, policy_version 4178 (0.0016)
|
| 1132 |
+
[2023-02-24 17:38:01,108][2364831] Updated weights for policy 0, policy_version 4188 (0.0011)
|
| 1133 |
+
[2023-02-24 17:38:01,266][2364708] Fps is (10 sec: 40550.7, 60 sec: 41028.2, 300 sec: 41182.2). Total num frames: 17154048. Throughput: 0: 10261.8. Samples: 3265563. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0)
|
| 1134 |
+
[2023-02-24 17:38:01,266][2364708] Avg episode reward: [(0, '35.841')]
|
| 1135 |
+
[2023-02-24 17:38:01,270][2364791] Saving new best policy, reward=35.841!
|
| 1136 |
+
[2023-02-24 17:38:02,155][2364831] Updated weights for policy 0, policy_version 4198 (0.0012)
|
| 1137 |
+
[2023-02-24 17:38:03,132][2364831] Updated weights for policy 0, policy_version 4208 (0.0009)
|
| 1138 |
+
[2023-02-24 17:38:04,177][2364831] Updated weights for policy 0, policy_version 4218 (0.0012)
|
| 1139 |
+
[2023-02-24 17:38:05,155][2364831] Updated weights for policy 0, policy_version 4228 (0.0013)
|
| 1140 |
+
[2023-02-24 17:38:06,137][2364831] Updated weights for policy 0, policy_version 4238 (0.0010)
|
| 1141 |
+
[2023-02-24 17:38:06,266][2364708] Fps is (10 sec: 40960.0, 60 sec: 41028.3, 300 sec: 41182.2). Total num frames: 17362944. Throughput: 0: 10260.6. Samples: 3327027. Policy #0 lag: (min: 1.0, avg: 2.0, max: 4.0)
|
| 1142 |
+
[2023-02-24 17:38:06,266][2364708] Avg episode reward: [(0, '34.701')]
|
| 1143 |
+
[2023-02-24 17:38:07,128][2364831] Updated weights for policy 0, policy_version 4248 (0.0010)
|
| 1144 |
+
[2023-02-24 17:38:08,120][2364831] Updated weights for policy 0, policy_version 4258 (0.0009)
|
| 1145 |
+
[2023-02-24 17:38:09,120][2364831] Updated weights for policy 0, policy_version 4268 (0.0010)
|
| 1146 |
+
[2023-02-24 17:38:10,112][2364831] Updated weights for policy 0, policy_version 4278 (0.0009)
|
| 1147 |
+
[2023-02-24 17:38:11,084][2364831] Updated weights for policy 0, policy_version 4288 (0.0009)
|
| 1148 |
+
[2023-02-24 17:38:11,266][2364708] Fps is (10 sec: 41368.9, 60 sec: 41028.1, 300 sec: 41182.1). Total num frames: 17567744. Throughput: 0: 10268.7. Samples: 3388911. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1149 |
+
[2023-02-24 17:38:11,267][2364708] Avg episode reward: [(0, '32.559')]
|
| 1150 |
+
[2023-02-24 17:38:12,108][2364831] Updated weights for policy 0, policy_version 4298 (0.0009)
|
| 1151 |
+
[2023-02-24 17:38:13,088][2364831] Updated weights for policy 0, policy_version 4308 (0.0011)
|
| 1152 |
+
[2023-02-24 17:38:14,094][2364831] Updated weights for policy 0, policy_version 4318 (0.0009)
|
| 1153 |
+
[2023-02-24 17:38:15,081][2364831] Updated weights for policy 0, policy_version 4328 (0.0009)
|
| 1154 |
+
[2023-02-24 17:38:16,054][2364831] Updated weights for policy 0, policy_version 4338 (0.0010)
|
| 1155 |
+
[2023-02-24 17:38:16,266][2364708] Fps is (10 sec: 40959.2, 60 sec: 41028.1, 300 sec: 41168.2). Total num frames: 17772544. Throughput: 0: 10274.2. Samples: 3419880. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 1156 |
+
[2023-02-24 17:38:16,267][2364708] Avg episode reward: [(0, '32.783')]
|
| 1157 |
+
[2023-02-24 17:38:17,103][2364831] Updated weights for policy 0, policy_version 4348 (0.0012)
|
| 1158 |
+
[2023-02-24 17:38:18,095][2364831] Updated weights for policy 0, policy_version 4358 (0.0009)
|
| 1159 |
+
[2023-02-24 17:38:19,078][2364831] Updated weights for policy 0, policy_version 4368 (0.0011)
|
| 1160 |
+
[2023-02-24 17:38:20,078][2364831] Updated weights for policy 0, policy_version 4378 (0.0012)
|
| 1161 |
+
[2023-02-24 17:38:21,065][2364831] Updated weights for policy 0, policy_version 4388 (0.0016)
|
| 1162 |
+
[2023-02-24 17:38:21,266][2364708] Fps is (10 sec: 41370.7, 60 sec: 41096.6, 300 sec: 41182.2). Total num frames: 17981440. Throughput: 0: 10262.9. Samples: 3481353. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1163 |
+
[2023-02-24 17:38:21,266][2364708] Avg episode reward: [(0, '35.299')]
|
| 1164 |
+
[2023-02-24 17:38:22,058][2364831] Updated weights for policy 0, policy_version 4398 (0.0012)
|
| 1165 |
+
[2023-02-24 17:38:23,045][2364831] Updated weights for policy 0, policy_version 4408 (0.0010)
|
| 1166 |
+
[2023-02-24 17:38:24,107][2364831] Updated weights for policy 0, policy_version 4418 (0.0011)
|
| 1167 |
+
[2023-02-24 17:38:25,058][2364831] Updated weights for policy 0, policy_version 4428 (0.0009)
|
| 1168 |
+
[2023-02-24 17:38:26,042][2364831] Updated weights for policy 0, policy_version 4438 (0.0012)
|
| 1169 |
+
[2023-02-24 17:38:26,266][2364708] Fps is (10 sec: 40960.7, 60 sec: 41028.2, 300 sec: 41154.4). Total num frames: 18182144. Throughput: 0: 10268.6. Samples: 3542961. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 1170 |
+
[2023-02-24 17:38:26,266][2364708] Avg episode reward: [(0, '33.602')]
|
| 1171 |
+
[2023-02-24 17:38:27,045][2364831] Updated weights for policy 0, policy_version 4448 (0.0013)
|
| 1172 |
+
[2023-02-24 17:38:28,079][2364831] Updated weights for policy 0, policy_version 4458 (0.0009)
|
| 1173 |
+
[2023-02-24 17:38:29,077][2364831] Updated weights for policy 0, policy_version 4468 (0.0012)
|
| 1174 |
+
[2023-02-24 17:38:30,014][2364831] Updated weights for policy 0, policy_version 4478 (0.0014)
|
| 1175 |
+
[2023-02-24 17:38:31,056][2364831] Updated weights for policy 0, policy_version 4488 (0.0014)
|
| 1176 |
+
[2023-02-24 17:38:31,266][2364708] Fps is (10 sec: 40959.3, 60 sec: 41096.5, 300 sec: 41168.3). Total num frames: 18391040. Throughput: 0: 10269.4. Samples: 3573768. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0)
|
| 1177 |
+
[2023-02-24 17:38:31,266][2364708] Avg episode reward: [(0, '30.251')]
|
| 1178 |
+
[2023-02-24 17:38:31,271][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004490_18391040.pth...
|
| 1179 |
+
[2023-02-24 17:38:31,336][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000002080_8519680.pth
|
| 1180 |
+
[2023-02-24 17:38:32,050][2364831] Updated weights for policy 0, policy_version 4498 (0.0012)
|
| 1181 |
+
[2023-02-24 17:38:33,042][2364831] Updated weights for policy 0, policy_version 4508 (0.0009)
|
| 1182 |
+
[2023-02-24 17:38:34,048][2364831] Updated weights for policy 0, policy_version 4518 (0.0010)
|
| 1183 |
+
[2023-02-24 17:38:35,020][2364831] Updated weights for policy 0, policy_version 4528 (0.0010)
|
| 1184 |
+
[2023-02-24 17:38:36,020][2364831] Updated weights for policy 0, policy_version 4538 (0.0010)
|
| 1185 |
+
[2023-02-24 17:38:36,266][2364708] Fps is (10 sec: 41369.6, 60 sec: 41096.5, 300 sec: 41140.5). Total num frames: 18595840. Throughput: 0: 10268.5. Samples: 3635388. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0)
|
| 1186 |
+
[2023-02-24 17:38:36,266][2364708] Avg episode reward: [(0, '34.728')]
|
| 1187 |
+
[2023-02-24 17:38:37,018][2364831] Updated weights for policy 0, policy_version 4548 (0.0012)
|
| 1188 |
+
[2023-02-24 17:38:37,996][2364831] Updated weights for policy 0, policy_version 4558 (0.0009)
|
| 1189 |
+
[2023-02-24 17:38:39,029][2364831] Updated weights for policy 0, policy_version 4568 (0.0010)
|
| 1190 |
+
[2023-02-24 17:38:40,017][2364831] Updated weights for policy 0, policy_version 4578 (0.0010)
|
| 1191 |
+
[2023-02-24 17:38:40,985][2364831] Updated weights for policy 0, policy_version 4588 (0.0010)
|
| 1192 |
+
[2023-02-24 17:38:41,266][2364708] Fps is (10 sec: 40959.9, 60 sec: 41096.4, 300 sec: 41154.4). Total num frames: 18800640. Throughput: 0: 10268.8. Samples: 3697023. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0)
|
| 1193 |
+
[2023-02-24 17:38:41,267][2364708] Avg episode reward: [(0, '32.483')]
|
| 1194 |
+
[2023-02-24 17:38:42,014][2364831] Updated weights for policy 0, policy_version 4598 (0.0014)
|
| 1195 |
+
[2023-02-24 17:38:42,975][2364831] Updated weights for policy 0, policy_version 4608 (0.0009)
|
| 1196 |
+
[2023-02-24 17:38:44,032][2364831] Updated weights for policy 0, policy_version 4618 (0.0009)
|
| 1197 |
+
[2023-02-24 17:38:45,014][2364831] Updated weights for policy 0, policy_version 4628 (0.0011)
|
| 1198 |
+
[2023-02-24 17:38:45,974][2364831] Updated weights for policy 0, policy_version 4638 (0.0012)
|
| 1199 |
+
[2023-02-24 17:38:46,266][2364708] Fps is (10 sec: 41370.5, 60 sec: 41164.9, 300 sec: 41168.3). Total num frames: 19009536. Throughput: 0: 10273.0. Samples: 3727845. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0)
|
| 1200 |
+
[2023-02-24 17:38:46,266][2364708] Avg episode reward: [(0, '34.188')]
|
| 1201 |
+
[2023-02-24 17:38:47,022][2364831] Updated weights for policy 0, policy_version 4648 (0.0014)
|
| 1202 |
+
[2023-02-24 17:38:48,027][2364831] Updated weights for policy 0, policy_version 4658 (0.0013)
|
| 1203 |
+
[2023-02-24 17:38:49,020][2364831] Updated weights for policy 0, policy_version 4668 (0.0010)
|
| 1204 |
+
[2023-02-24 17:38:50,024][2364831] Updated weights for policy 0, policy_version 4678 (0.0010)
|
| 1205 |
+
[2023-02-24 17:38:51,024][2364831] Updated weights for policy 0, policy_version 4688 (0.0011)
|
| 1206 |
+
[2023-02-24 17:38:51,266][2364708] Fps is (10 sec: 40960.4, 60 sec: 41028.3, 300 sec: 41140.5). Total num frames: 19210240. Throughput: 0: 10270.9. Samples: 3789216. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0)
|
| 1207 |
+
[2023-02-24 17:38:51,266][2364708] Avg episode reward: [(0, '36.140')]
|
| 1208 |
+
[2023-02-24 17:38:51,270][2364791] Saving new best policy, reward=36.140!
|
| 1209 |
+
[2023-02-24 17:38:52,009][2364831] Updated weights for policy 0, policy_version 4698 (0.0012)
|
| 1210 |
+
[2023-02-24 17:38:53,006][2364831] Updated weights for policy 0, policy_version 4708 (0.0011)
|
| 1211 |
+
[2023-02-24 17:38:54,017][2364831] Updated weights for policy 0, policy_version 4718 (0.0012)
|
| 1212 |
+
[2023-02-24 17:38:54,981][2364831] Updated weights for policy 0, policy_version 4728 (0.0011)
|
| 1213 |
+
[2023-02-24 17:38:55,968][2364831] Updated weights for policy 0, policy_version 4738 (0.0012)
|
| 1214 |
+
[2023-02-24 17:38:56,266][2364708] Fps is (10 sec: 40959.4, 60 sec: 41096.6, 300 sec: 41154.4). Total num frames: 19419136. Throughput: 0: 10265.0. Samples: 3850833. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0)
|
| 1215 |
+
[2023-02-24 17:38:56,266][2364708] Avg episode reward: [(0, '32.669')]
|
| 1216 |
+
[2023-02-24 17:38:56,994][2364831] Updated weights for policy 0, policy_version 4748 (0.0011)
|
| 1217 |
+
[2023-02-24 17:38:57,985][2364831] Updated weights for policy 0, policy_version 4758 (0.0008)
|
| 1218 |
+
[2023-02-24 17:38:58,970][2364831] Updated weights for policy 0, policy_version 4768 (0.0010)
|
| 1219 |
+
[2023-02-24 17:38:59,953][2364831] Updated weights for policy 0, policy_version 4778 (0.0010)
|
| 1220 |
+
[2023-02-24 17:39:00,969][2364831] Updated weights for policy 0, policy_version 4788 (0.0012)
|
| 1221 |
+
[2023-02-24 17:39:01,266][2364708] Fps is (10 sec: 41369.3, 60 sec: 41164.8, 300 sec: 41140.5). Total num frames: 19623936. Throughput: 0: 10264.2. Samples: 3881769. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1222 |
+
[2023-02-24 17:39:01,266][2364708] Avg episode reward: [(0, '33.503')]
|
| 1223 |
+
[2023-02-24 17:39:01,956][2364831] Updated weights for policy 0, policy_version 4798 (0.0011)
|
| 1224 |
+
[2023-02-24 17:39:02,959][2364831] Updated weights for policy 0, policy_version 4808 (0.0009)
|
| 1225 |
+
[2023-02-24 17:39:03,937][2364831] Updated weights for policy 0, policy_version 4818 (0.0010)
|
| 1226 |
+
[2023-02-24 17:39:04,994][2364831] Updated weights for policy 0, policy_version 4828 (0.0012)
|
| 1227 |
+
[2023-02-24 17:39:05,948][2364831] Updated weights for policy 0, policy_version 4838 (0.0009)
|
| 1228 |
+
[2023-02-24 17:39:06,266][2364708] Fps is (10 sec: 40959.8, 60 sec: 41096.5, 300 sec: 41140.5). Total num frames: 19828736. Throughput: 0: 10266.0. Samples: 3943326. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0)
|
| 1229 |
+
[2023-02-24 17:39:06,266][2364708] Avg episode reward: [(0, '33.048')]
|
| 1230 |
+
[2023-02-24 17:39:06,927][2364831] Updated weights for policy 0, policy_version 4848 (0.0009)
|
| 1231 |
+
[2023-02-24 17:39:07,963][2364831] Updated weights for policy 0, policy_version 4858 (0.0010)
|
| 1232 |
+
[2023-02-24 17:39:08,957][2364831] Updated weights for policy 0, policy_version 4868 (0.0013)
|
| 1233 |
+
[2023-02-24 17:39:09,952][2364831] Updated weights for policy 0, policy_version 4878 (0.0009)
|
| 1234 |
+
[2023-02-24 17:39:10,563][2364791] Stopping Batcher_0...
|
| 1235 |
+
[2023-02-24 17:39:10,563][2364708] Component Batcher_0 stopped!
|
| 1236 |
+
[2023-02-24 17:39:10,564][2364791] Loop batcher_evt_loop terminating...
|
| 1237 |
+
[2023-02-24 17:39:10,566][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
|
| 1238 |
+
[2023-02-24 17:39:10,580][2365108] Stopping RolloutWorker_w15...
|
| 1239 |
+
[2023-02-24 17:39:10,580][2364708] Component RolloutWorker_w15 stopped!
|
| 1240 |
+
[2023-02-24 17:39:10,580][2364862] Stopping RolloutWorker_w14...
|
| 1241 |
+
[2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w14 stopped!
|
| 1242 |
+
[2023-02-24 17:39:10,581][2364855] Stopping RolloutWorker_w10...
|
| 1243 |
+
[2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w10 stopped!
|
| 1244 |
+
[2023-02-24 17:39:10,581][2364855] Loop rollout_proc10_evt_loop terminating...
|
| 1245 |
+
[2023-02-24 17:39:10,581][2364708] Component RolloutWorker_w0 stopped!
|
| 1246 |
+
[2023-02-24 17:39:10,581][2365108] Loop rollout_proc15_evt_loop terminating...
|
| 1247 |
+
[2023-02-24 17:39:10,581][2364832] Stopping RolloutWorker_w0...
|
| 1248 |
+
[2023-02-24 17:39:10,582][2364862] Loop rollout_proc14_evt_loop terminating...
|
| 1249 |
+
[2023-02-24 17:39:10,582][2364708] Component RolloutWorker_w3 stopped!
|
| 1250 |
+
[2023-02-24 17:39:10,582][2364836] Stopping RolloutWorker_w3...
|
| 1251 |
+
[2023-02-24 17:39:10,582][2364857] Stopping RolloutWorker_w11...
|
| 1252 |
+
[2023-02-24 17:39:10,582][2364832] Loop rollout_proc0_evt_loop terminating...
|
| 1253 |
+
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w11 stopped!
|
| 1254 |
+
[2023-02-24 17:39:10,583][2364836] Loop rollout_proc3_evt_loop terminating...
|
| 1255 |
+
[2023-02-24 17:39:10,583][2364859] Stopping RolloutWorker_w8...
|
| 1256 |
+
[2023-02-24 17:39:10,583][2364857] Loop rollout_proc11_evt_loop terminating...
|
| 1257 |
+
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w8 stopped!
|
| 1258 |
+
[2023-02-24 17:39:10,583][2364861] Stopping RolloutWorker_w13...
|
| 1259 |
+
[2023-02-24 17:39:10,583][2364833] Stopping RolloutWorker_w1...
|
| 1260 |
+
[2023-02-24 17:39:10,583][2364839] Stopping RolloutWorker_w7...
|
| 1261 |
+
[2023-02-24 17:39:10,583][2364838] Stopping RolloutWorker_w6...
|
| 1262 |
+
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w13 stopped!
|
| 1263 |
+
[2023-02-24 17:39:10,583][2364861] Loop rollout_proc13_evt_loop terminating...
|
| 1264 |
+
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w1 stopped!
|
| 1265 |
+
[2023-02-24 17:39:10,583][2364833] Loop rollout_proc1_evt_loop terminating...
|
| 1266 |
+
[2023-02-24 17:39:10,583][2364838] Loop rollout_proc6_evt_loop terminating...
|
| 1267 |
+
[2023-02-24 17:39:10,583][2364839] Loop rollout_proc7_evt_loop terminating...
|
| 1268 |
+
[2023-02-24 17:39:10,583][2364860] Stopping RolloutWorker_w12...
|
| 1269 |
+
[2023-02-24 17:39:10,583][2364708] Component RolloutWorker_w7 stopped!
|
| 1270 |
+
[2023-02-24 17:39:10,584][2364708] Component RolloutWorker_w6 stopped!
|
| 1271 |
+
[2023-02-24 17:39:10,584][2364860] Loop rollout_proc12_evt_loop terminating...
|
| 1272 |
+
[2023-02-24 17:39:10,584][2364708] Component RolloutWorker_w12 stopped!
|
| 1273 |
+
[2023-02-24 17:39:10,583][2364859] Loop rollout_proc8_evt_loop terminating...
|
| 1274 |
+
[2023-02-24 17:39:10,585][2364708] Component RolloutWorker_w9 stopped!
|
| 1275 |
+
[2023-02-24 17:39:10,585][2364856] Stopping RolloutWorker_w9...
|
| 1276 |
+
[2023-02-24 17:39:10,585][2364856] Loop rollout_proc9_evt_loop terminating...
|
| 1277 |
+
[2023-02-24 17:39:10,585][2364708] Component RolloutWorker_w4 stopped!
|
| 1278 |
+
[2023-02-24 17:39:10,585][2364835] Stopping RolloutWorker_w4...
|
| 1279 |
+
[2023-02-24 17:39:10,586][2364835] Loop rollout_proc4_evt_loop terminating...
|
| 1280 |
+
[2023-02-24 17:39:10,591][2364831] Weights refcount: 2 0
|
| 1281 |
+
[2023-02-24 17:39:10,596][2364831] Stopping InferenceWorker_p0-w0...
|
| 1282 |
+
[2023-02-24 17:39:10,596][2364708] Component InferenceWorker_p0-w0 stopped!
|
| 1283 |
+
[2023-02-24 17:39:10,596][2364831] Loop inference_proc0-0_evt_loop terminating...
|
| 1284 |
+
[2023-02-24 17:39:10,664][2364791] Removing /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000003287_13463552.pth
|
| 1285 |
+
[2023-02-24 17:39:10,667][2364837] Stopping RolloutWorker_w5...
|
| 1286 |
+
[2023-02-24 17:39:10,667][2364708] Component RolloutWorker_w5 stopped!
|
| 1287 |
+
[2023-02-24 17:39:10,667][2364837] Loop rollout_proc5_evt_loop terminating...
|
| 1288 |
+
[2023-02-24 17:39:10,675][2364791] Saving /home/sebas/research/hugging-face-course/vizdoom/train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
|
| 1289 |
+
[2023-02-24 17:39:10,679][2364834] Stopping RolloutWorker_w2...
|
| 1290 |
+
[2023-02-24 17:39:10,679][2364708] Component RolloutWorker_w2 stopped!
|
| 1291 |
+
[2023-02-24 17:39:10,679][2364834] Loop rollout_proc2_evt_loop terminating...
|
| 1292 |
+
[2023-02-24 17:39:10,810][2364791] Stopping LearnerWorker_p0...
|
| 1293 |
+
[2023-02-24 17:39:10,810][2364708] Component LearnerWorker_p0 stopped!
|
| 1294 |
+
[2023-02-24 17:39:10,811][2364791] Loop learner_proc0_evt_loop terminating...
|
| 1295 |
+
[2023-02-24 17:39:10,811][2364708] Waiting for process learner_proc0 to stop...
|
| 1296 |
+
[2023-02-24 17:39:11,642][2364708] Waiting for process inference_proc0-0 to join...
|
| 1297 |
+
[2023-02-24 17:39:11,642][2364708] Waiting for process rollout_proc0 to join...
|
| 1298 |
+
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc1 to join...
|
| 1299 |
+
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc2 to join...
|
| 1300 |
+
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc3 to join...
|
| 1301 |
+
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc4 to join...
|
| 1302 |
+
[2023-02-24 17:39:11,643][2364708] Waiting for process rollout_proc5 to join...
|
| 1303 |
+
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc6 to join...
|
| 1304 |
+
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc7 to join...
|
| 1305 |
+
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc8 to join...
|
| 1306 |
+
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc9 to join...
|
| 1307 |
+
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc10 to join...
|
| 1308 |
+
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc11 to join...
|
| 1309 |
+
[2023-02-24 17:39:11,644][2364708] Waiting for process rollout_proc12 to join...
|
| 1310 |
+
[2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc13 to join...
|
| 1311 |
+
[2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc14 to join...
|
| 1312 |
+
[2023-02-24 17:39:11,645][2364708] Waiting for process rollout_proc15 to join...
|
| 1313 |
+
[2023-02-24 17:39:11,645][2364708] Batcher 0 profile tree view:
|
| 1314 |
+
batching: 73.4519, releasing_batches: 0.1153
|
| 1315 |
+
[2023-02-24 17:39:11,645][2364708] InferenceWorker_p0-w0 profile tree view:
|
| 1316 |
+
wait_policy: 0.0001
|
| 1317 |
+
wait_policy_total: 14.4354
|
| 1318 |
+
update_model: 8.0668
|
| 1319 |
+
weight_update: 0.0009
|
| 1320 |
+
one_step: 0.0083
|
| 1321 |
+
handle_policy_step: 352.4861
|
| 1322 |
+
deserialize: 37.8441, stack: 1.8339, obs_to_device_normalize: 110.8509, forward: 112.2633, send_messages: 30.0739
|
| 1323 |
+
prepare_outputs: 46.8292
|
| 1324 |
+
to_cpu: 31.2023
|
| 1325 |
+
[2023-02-24 17:39:11,646][2364708] Learner 0 profile tree view:
|
| 1326 |
+
misc: 0.0142, prepare_batch: 21.8985
|
| 1327 |
+
train: 88.0533
|
| 1328 |
+
epoch_init: 0.0176, minibatch_init: 0.0202, losses_postprocess: 1.0969, kl_divergence: 0.8556, after_optimizer: 0.9595
|
| 1329 |
+
calculate_losses: 27.5889
|
| 1330 |
+
losses_init: 0.0102, forward_head: 2.8021, bptt_initial: 14.7305, tail: 1.9333, advantages_returns: 0.5209, losses: 3.3108
|
| 1331 |
+
bptt: 3.7098
|
| 1332 |
+
bptt_forward_core: 3.5507
|
| 1333 |
+
update: 56.2303
|
| 1334 |
+
clip: 3.0247
|
| 1335 |
+
[2023-02-24 17:39:11,646][2364708] RolloutWorker_w0 profile tree view:
|
| 1336 |
+
wait_for_trajectories: 0.1784, enqueue_policy_requests: 13.5703, env_step: 193.6379, overhead: 19.5570, complete_rollouts: 0.3859
|
| 1337 |
+
save_policy_outputs: 14.2004
|
| 1338 |
+
split_output_tensors: 6.7511
|
| 1339 |
+
[2023-02-24 17:39:11,646][2364708] RolloutWorker_w15 profile tree view:
|
| 1340 |
+
wait_for_trajectories: 0.1858, enqueue_policy_requests: 14.0534, env_step: 199.4115, overhead: 20.2979, complete_rollouts: 0.3205
|
| 1341 |
+
save_policy_outputs: 14.6899
|
| 1342 |
+
split_output_tensors: 6.9819
|
| 1343 |
+
[2023-02-24 17:39:11,646][2364708] Loop Runner_EvtLoop terminating...
|
| 1344 |
+
[2023-02-24 17:39:11,646][2364708] Runner profile tree view:
|
| 1345 |
+
main_loop: 398.6762
|
| 1346 |
+
[2023-02-24 17:39:11,647][2364708] Collected {0: 20004864}, FPS: 40130.2
|
| 1347 |
+
[2023-02-24 17:39:11,652][2364708] Loading existing experiment configuration from train_dir/default_experiment/config.json
|
| 1348 |
+
[2023-02-24 17:39:11,652][2364708] Overriding arg 'train_dir' with value 'train_dir' passed from command line
|
| 1349 |
+
[2023-02-24 17:39:11,652][2364708] Overriding arg 'num_workers' with value 1 passed from command line
|
| 1350 |
+
[2023-02-24 17:39:11,652][2364708] Adding new argument 'no_render'=True that is not in the saved config file!
|
| 1351 |
+
[2023-02-24 17:39:11,652][2364708] Adding new argument 'save_video'=True that is not in the saved config file!
|
| 1352 |
+
[2023-02-24 17:39:11,652][2364708] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
| 1353 |
+
[2023-02-24 17:39:11,652][2364708] Adding new argument 'video_name'=None that is not in the saved config file!
|
| 1354 |
+
[2023-02-24 17:39:11,652][2364708] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
| 1355 |
+
[2023-02-24 17:39:11,653][2364708] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
| 1356 |
+
[2023-02-24 17:39:11,653][2364708] Adding new argument 'push_to_hub'=True that is not in the saved config file!
|
| 1357 |
+
[2023-02-24 17:39:11,653][2364708] Adding new argument 'hf_repository'='eldraco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
|
| 1358 |
+
[2023-02-24 17:39:11,653][2364708] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
| 1359 |
+
[2023-02-24 17:39:11,653][2364708] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
| 1360 |
+
[2023-02-24 17:39:11,653][2364708] Adding new argument 'train_script'=None that is not in the saved config file!
|
| 1361 |
+
[2023-02-24 17:39:11,653][2364708] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
| 1362 |
+
[2023-02-24 17:39:11,653][2364708] Using frameskip 1 and render_action_repeat=4 for evaluation
|
| 1363 |
+
[2023-02-24 17:39:11,659][2364708] Doom resolution: 160x120, resize resolution: (128, 72)
|
| 1364 |
+
[2023-02-24 17:39:11,659][2364708] RunningMeanStd input shape: (3, 72, 128)
|
| 1365 |
+
[2023-02-24 17:39:11,660][2364708] RunningMeanStd input shape: (1,)
|
| 1366 |
+
[2023-02-24 17:39:11,667][2364708] ConvEncoder: input_channels=3
|
| 1367 |
+
[2023-02-24 17:39:11,779][2364708] Conv encoder output size: 512
|
| 1368 |
+
[2023-02-24 17:39:11,779][2364708] Policy head output size: 512
|
| 1369 |
+
[2023-02-24 17:39:13,104][2364708] Loading state from checkpoint train_dir/default_experiment/checkpoint_p0/checkpoint_000004884_20004864.pth...
|
| 1370 |
+
[2023-02-24 17:39:13,883][2364708] Num frames 100...
|
| 1371 |
+
[2023-02-24 17:39:13,953][2364708] Num frames 200...
|
| 1372 |
+
[2023-02-24 17:39:14,021][2364708] Num frames 300...
|
| 1373 |
+
[2023-02-24 17:39:14,089][2364708] Num frames 400...
|
| 1374 |
+
[2023-02-24 17:39:14,160][2364708] Num frames 500...
|
| 1375 |
+
[2023-02-24 17:39:14,229][2364708] Num frames 600...
|
| 1376 |
+
[2023-02-24 17:39:14,297][2364708] Num frames 700...
|
| 1377 |
+
[2023-02-24 17:39:14,365][2364708] Num frames 800...
|
| 1378 |
+
[2023-02-24 17:39:14,435][2364708] Num frames 900...
|
| 1379 |
+
[2023-02-24 17:39:14,505][2364708] Num frames 1000...
|
| 1380 |
+
[2023-02-24 17:39:14,575][2364708] Num frames 1100...
|
| 1381 |
+
[2023-02-24 17:39:14,645][2364708] Num frames 1200...
|
| 1382 |
+
[2023-02-24 17:39:14,714][2364708] Num frames 1300...
|
| 1383 |
+
[2023-02-24 17:39:14,784][2364708] Num frames 1400...
|
| 1384 |
+
[2023-02-24 17:39:14,886][2364708] Avg episode rewards: #0: 34.720, true rewards: #0: 14.720
|
| 1385 |
+
[2023-02-24 17:39:14,887][2364708] Avg episode reward: 34.720, avg true_objective: 14.720
|
| 1386 |
+
[2023-02-24 17:39:14,917][2364708] Num frames 1500...
|
| 1387 |
+
[2023-02-24 17:39:14,998][2364708] Num frames 1600...
|
| 1388 |
+
[2023-02-24 17:39:15,067][2364708] Num frames 1700...
|
| 1389 |
+
[2023-02-24 17:39:15,138][2364708] Num frames 1800...
|
| 1390 |
+
[2023-02-24 17:39:15,208][2364708] Num frames 1900...
|
| 1391 |
+
[2023-02-24 17:39:15,277][2364708] Num frames 2000...
|
| 1392 |
+
[2023-02-24 17:39:15,347][2364708] Num frames 2100...
|
| 1393 |
+
[2023-02-24 17:39:15,415][2364708] Num frames 2200...
|
| 1394 |
+
[2023-02-24 17:39:15,485][2364708] Num frames 2300...
|
| 1395 |
+
[2023-02-24 17:39:15,554][2364708] Num frames 2400...
|
| 1396 |
+
[2023-02-24 17:39:15,621][2364708] Num frames 2500...
|
| 1397 |
+
[2023-02-24 17:39:15,714][2364708] Avg episode rewards: #0: 31.300, true rewards: #0: 12.800
|
| 1398 |
+
[2023-02-24 17:39:15,715][2364708] Avg episode reward: 31.300, avg true_objective: 12.800
|
| 1399 |
+
[2023-02-24 17:39:15,758][2364708] Num frames 2600...
|
| 1400 |
+
[2023-02-24 17:39:15,831][2364708] Num frames 2700...
|
| 1401 |
+
[2023-02-24 17:39:15,900][2364708] Num frames 2800...
|
| 1402 |
+
[2023-02-24 17:39:15,969][2364708] Num frames 2900...
|
| 1403 |
+
[2023-02-24 17:39:16,037][2364708] Num frames 3000...
|
| 1404 |
+
[2023-02-24 17:39:16,106][2364708] Num frames 3100...
|
| 1405 |
+
[2023-02-24 17:39:16,177][2364708] Num frames 3200...
|
| 1406 |
+
[2023-02-24 17:39:16,247][2364708] Num frames 3300...
|
| 1407 |
+
[2023-02-24 17:39:16,316][2364708] Num frames 3400...
|
| 1408 |
+
[2023-02-24 17:39:16,386][2364708] Num frames 3500...
|
| 1409 |
+
[2023-02-24 17:39:16,455][2364708] Num frames 3600...
|
| 1410 |
+
[2023-02-24 17:39:16,526][2364708] Num frames 3700...
|
| 1411 |
+
[2023-02-24 17:39:16,596][2364708] Num frames 3800...
|
| 1412 |
+
[2023-02-24 17:39:16,665][2364708] Num frames 3900...
|
| 1413 |
+
[2023-02-24 17:39:16,734][2364708] Num frames 4000...
|
| 1414 |
+
[2023-02-24 17:39:16,802][2364708] Num frames 4100...
|
| 1415 |
+
[2023-02-24 17:39:16,871][2364708] Num frames 4200...
|
| 1416 |
+
[2023-02-24 17:39:16,941][2364708] Num frames 4300...
|
| 1417 |
+
[2023-02-24 17:39:17,010][2364708] Num frames 4400...
|
| 1418 |
+
[2023-02-24 17:39:17,078][2364708] Num frames 4500...
|
| 1419 |
+
[2023-02-24 17:39:17,148][2364708] Num frames 4600...
|
| 1420 |
+
[2023-02-24 17:39:17,244][2364708] Avg episode rewards: #0: 41.533, true rewards: #0: 15.533
|
| 1421 |
+
[2023-02-24 17:39:17,244][2364708] Avg episode reward: 41.533, avg true_objective: 15.533
|
| 1422 |
+
[2023-02-24 17:39:17,288][2364708] Num frames 4700...
|
| 1423 |
+
[2023-02-24 17:39:17,360][2364708] Num frames 4800...
|
| 1424 |
+
[2023-02-24 17:39:17,430][2364708] Num frames 4900...
|
| 1425 |
+
[2023-02-24 17:39:17,499][2364708] Num frames 5000...
|
| 1426 |
+
[2023-02-24 17:39:17,569][2364708] Num frames 5100...
|
| 1427 |
+
[2023-02-24 17:39:17,640][2364708] Num frames 5200...
|
| 1428 |
+
[2023-02-24 17:39:17,720][2364708] Avg episode rewards: #0: 34.100, true rewards: #0: 13.100
|
| 1429 |
+
[2023-02-24 17:39:17,720][2364708] Avg episode reward: 34.100, avg true_objective: 13.100
|
| 1430 |
+
[2023-02-24 17:39:17,789][2364708] Num frames 5300...
|
| 1431 |
+
[2023-02-24 17:39:17,857][2364708] Num frames 5400...
|
| 1432 |
+
[2023-02-24 17:39:17,926][2364708] Num frames 5500...
|
| 1433 |
+
[2023-02-24 17:39:17,995][2364708] Num frames 5600...
|
| 1434 |
+
[2023-02-24 17:39:18,063][2364708] Num frames 5700...
|
| 1435 |
+
[2023-02-24 17:39:18,132][2364708] Num frames 5800...
|
| 1436 |
+
[2023-02-24 17:39:18,195][2364708] Avg episode rewards: #0: 29.232, true rewards: #0: 11.632
|
| 1437 |
+
[2023-02-24 17:39:18,195][2364708] Avg episode reward: 29.232, avg true_objective: 11.632
|
| 1438 |
+
[2023-02-24 17:39:18,273][2364708] Num frames 5900...
|
| 1439 |
+
[2023-02-24 17:39:18,342][2364708] Num frames 6000...
|
| 1440 |
+
[2023-02-24 17:39:18,409][2364708] Num frames 6100...
|
| 1441 |
+
[2023-02-24 17:39:18,482][2364708] Num frames 6200...
|
| 1442 |
+
[2023-02-24 17:39:18,552][2364708] Num frames 6300...
|
| 1443 |
+
[2023-02-24 17:39:18,646][2364708] Avg episode rewards: #0: 25.600, true rewards: #0: 10.600
|
| 1444 |
+
[2023-02-24 17:39:18,646][2364708] Avg episode reward: 25.600, avg true_objective: 10.600
|
| 1445 |
+
[2023-02-24 17:39:18,691][2364708] Num frames 6400...
|
| 1446 |
+
[2023-02-24 17:39:18,767][2364708] Num frames 6500...
|
| 1447 |
+
[2023-02-24 17:39:18,835][2364708] Num frames 6600...
|
| 1448 |
+
[2023-02-24 17:39:18,904][2364708] Num frames 6700...
|
| 1449 |
+
[2023-02-24 17:39:18,972][2364708] Num frames 6800...
|
| 1450 |
+
[2023-02-24 17:39:19,041][2364708] Num frames 6900...
|
| 1451 |
+
[2023-02-24 17:39:19,110][2364708] Num frames 7000...
|
| 1452 |
+
[2023-02-24 17:39:19,179][2364708] Num frames 7100...
|
| 1453 |
+
[2023-02-24 17:39:19,249][2364708] Num frames 7200...
|
| 1454 |
+
[2023-02-24 17:39:19,318][2364708] Num frames 7300...
|
| 1455 |
+
[2023-02-24 17:39:19,388][2364708] Num frames 7400...
|
| 1456 |
+
[2023-02-24 17:39:19,458][2364708] Num frames 7500...
|
| 1457 |
+
[2023-02-24 17:39:19,528][2364708] Num frames 7600...
|
| 1458 |
+
[2023-02-24 17:39:19,598][2364708] Num frames 7700...
|
| 1459 |
+
[2023-02-24 17:39:19,667][2364708] Num frames 7800...
|
| 1460 |
+
[2023-02-24 17:39:19,736][2364708] Num frames 7900...
|
| 1461 |
+
[2023-02-24 17:39:19,808][2364708] Avg episode rewards: #0: 28.040, true rewards: #0: 11.326
|
| 1462 |
+
[2023-02-24 17:39:19,808][2364708] Avg episode reward: 28.040, avg true_objective: 11.326
|
| 1463 |
+
[2023-02-24 17:39:19,879][2364708] Num frames 8000...
|
| 1464 |
+
[2023-02-24 17:39:19,948][2364708] Num frames 8100...
|
| 1465 |
+
[2023-02-24 17:39:20,017][2364708] Num frames 8200...
|
| 1466 |
+
[2023-02-24 17:39:20,086][2364708] Num frames 8300...
|
| 1467 |
+
[2023-02-24 17:39:20,155][2364708] Num frames 8400...
|
| 1468 |
+
[2023-02-24 17:39:20,225][2364708] Num frames 8500...
|
| 1469 |
+
[2023-02-24 17:39:20,294][2364708] Num frames 8600...
|
| 1470 |
+
[2023-02-24 17:39:20,363][2364708] Num frames 8700...
|
| 1471 |
+
[2023-02-24 17:39:20,432][2364708] Num frames 8800...
|
| 1472 |
+
[2023-02-24 17:39:20,501][2364708] Num frames 8900...
|
| 1473 |
+
[2023-02-24 17:39:20,571][2364708] Num frames 9000...
|
| 1474 |
+
[2023-02-24 17:39:20,640][2364708] Num frames 9100...
|
| 1475 |
+
[2023-02-24 17:39:20,711][2364708] Num frames 9200...
|
| 1476 |
+
[2023-02-24 17:39:20,781][2364708] Num frames 9300...
|
| 1477 |
+
[2023-02-24 17:39:20,850][2364708] Num frames 9400...
|
| 1478 |
+
[2023-02-24 17:39:20,919][2364708] Num frames 9500...
|
| 1479 |
+
[2023-02-24 17:39:20,990][2364708] Num frames 9600...
|
| 1480 |
+
[2023-02-24 17:39:21,060][2364708] Num frames 9700...
|
| 1481 |
+
[2023-02-24 17:39:21,130][2364708] Num frames 9800...
|
| 1482 |
+
[2023-02-24 17:39:21,198][2364708] Num frames 9900...
|
| 1483 |
+
[2023-02-24 17:39:21,269][2364708] Num frames 10000...
|
| 1484 |
+
[2023-02-24 17:39:21,341][2364708] Avg episode rewards: #0: 32.035, true rewards: #0: 12.535
|
| 1485 |
+
[2023-02-24 17:39:21,341][2364708] Avg episode reward: 32.035, avg true_objective: 12.535
|
| 1486 |
+
[2023-02-24 17:39:21,412][2364708] Num frames 10100...
|
| 1487 |
+
[2023-02-24 17:39:21,481][2364708] Num frames 10200...
|
| 1488 |
+
[2023-02-24 17:39:21,551][2364708] Num frames 10300...
|
| 1489 |
+
[2023-02-24 17:39:21,621][2364708] Num frames 10400...
|
| 1490 |
+
[2023-02-24 17:39:21,691][2364708] Num frames 10500...
|
| 1491 |
+
[2023-02-24 17:39:21,759][2364708] Num frames 10600...
|
| 1492 |
+
[2023-02-24 17:39:21,828][2364708] Num frames 10700...
|
| 1493 |
+
[2023-02-24 17:39:21,897][2364708] Num frames 10800...
|
| 1494 |
+
[2023-02-24 17:39:21,966][2364708] Num frames 10900...
|
| 1495 |
+
[2023-02-24 17:39:22,035][2364708] Num frames 11000...
|
| 1496 |
+
[2023-02-24 17:39:22,117][2364708] Avg episode rewards: #0: 31.603, true rewards: #0: 12.270
|
| 1497 |
+
[2023-02-24 17:39:22,118][2364708] Avg episode reward: 31.603, avg true_objective: 12.270
|
| 1498 |
+
[2023-02-24 17:39:22,180][2364708] Num frames 11100...
|
| 1499 |
+
[2023-02-24 17:39:22,251][2364708] Num frames 11200...
|
| 1500 |
+
[2023-02-24 17:39:22,320][2364708] Num frames 11300...
|
| 1501 |
+
[2023-02-24 17:39:22,389][2364708] Num frames 11400...
|
| 1502 |
+
[2023-02-24 17:39:22,458][2364708] Num frames 11500...
|
| 1503 |
+
[2023-02-24 17:39:22,527][2364708] Num frames 11600...
|
| 1504 |
+
[2023-02-24 17:39:22,596][2364708] Num frames 11700...
|
| 1505 |
+
[2023-02-24 17:39:22,666][2364708] Num frames 11800...
|
| 1506 |
+
[2023-02-24 17:39:22,735][2364708] Num frames 11900...
|
| 1507 |
+
[2023-02-24 17:39:22,804][2364708] Num frames 12000...
|
| 1508 |
+
[2023-02-24 17:39:22,874][2364708] Num frames 12100...
|
| 1509 |
+
[2023-02-24 17:39:22,944][2364708] Num frames 12200...
|
| 1510 |
+
[2023-02-24 17:39:23,013][2364708] Num frames 12300...
|
| 1511 |
+
[2023-02-24 17:39:23,082][2364708] Num frames 12400...
|
| 1512 |
+
[2023-02-24 17:39:23,152][2364708] Num frames 12500...
|
| 1513 |
+
[2023-02-24 17:39:23,220][2364708] Num frames 12600...
|
| 1514 |
+
[2023-02-24 17:39:23,289][2364708] Num frames 12700...
|
| 1515 |
+
[2023-02-24 17:39:23,360][2364708] Num frames 12800...
|
| 1516 |
+
[2023-02-24 17:39:23,433][2364708] Avg episode rewards: #0: 33.229, true rewards: #0: 12.829
|
| 1517 |
+
[2023-02-24 17:39:23,433][2364708] Avg episode reward: 33.229, avg true_objective: 12.829
|
| 1518 |
+
[2023-02-24 17:39:39,087][2364708] Replay video saved to train_dir/default_experiment/replay.mp4!
|