Taratata commited on
Commit
f3adcbc
·
1 Parent(s): 9a58791

Initial commit

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ model-index:
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
- value: -21.00 +/- 0.00
20
  name: mean_reward
21
  verified: false
22
  ---
@@ -72,7 +72,7 @@ OrderedDict([('batch_size', 32),
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
- ('n_timesteps', 100000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
 
16
  type: PongNoFrameskip-v4
17
  metrics:
18
  - type: mean_reward
19
+ value: -20.60 +/- 0.92
20
  name: mean_reward
21
  verified: false
22
  ---
 
72
  ('gradient_steps', 1),
73
  ('learning_rate', 0.0001),
74
  ('learning_starts', 100000),
75
+ ('n_timesteps', 200000.0),
76
  ('optimize_memory_usage', False),
77
  ('policy', 'CnnPolicy'),
78
  ('target_update_interval', 1000),
args.yml CHANGED
@@ -54,7 +54,7 @@
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
- - 4291397145
58
  - - storage
59
  - null
60
  - - study_name
 
54
  - - save_replay_buffer
55
  - false
56
  - - seed
57
+ - 3583354604
58
  - - storage
59
  - null
60
  - - study_name
config.yml CHANGED
@@ -18,7 +18,7 @@
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
- - 100000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
 
18
  - - learning_starts
19
  - 100000
20
  - - n_timesteps
21
+ - 200000.0
22
  - - optimize_memory_usage
23
  - false
24
  - - policy
dqn-PongNoFrameskip-v4.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84f8ac7b857f3b48226e15202a0ece88470c78c4fd79363606ea4c6ff60e176f
3
- size 13719746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2919c21849acac4f144df0fee5a943815304208cb13ed52f4380e3dffa577a18
3
+ size 27224802
dqn-PongNoFrameskip-v4/data CHANGED
The diff for this file is too large to render. See raw diff
 
dqn-PongNoFrameskip-v4/policy.optimizer.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1e067afe9912f3dd1b7925918b8cbe439229f6008e572c9c7e431ae731419f1
3
- size 687
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31e2d323b4f81782fcde1c62d2ae4caa8b8f4475b750c0785d4e46ac745e6f14
3
+ size 13505739
dqn-PongNoFrameskip-v4/policy.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c02817f5ed705edcf80e74c2404c1463fcac9ebe112ebd87a6e50295851a5c9c
3
  size 13504937
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11010d8b9116aeec11ffeacc516d28fed7bf82e9388eda1b5b1aea17df51268c
3
  size 13504937
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96f60e1f64134d580fe85bec2d75ae24678756708ec9f746e32f5f4ab5e6f652
3
- size 49746
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c07944d0675eda11092738b33d590d07979274c87243d956960844a0223ee3f
3
+ size 64778
results.json CHANGED
@@ -1 +1 @@
1
- {"mean_reward": -21.0, "std_reward": 0.0, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-16T16:56:26.260303"}
 
1
+ {"mean_reward": -20.6, "std_reward": 0.9165151389911681, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-16T17:48:07.128553"}
train_eval_metrics.zip CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:053cf5a4928ec9725af6928965addb9b67f21cf2e11e9fd201fda7b699b4e902
3
- size 3816
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc318d165a9ecd80ba2cab6032a03495f7359e522a8a2ba1f0d481349f69ed5a
3
+ size 6927