Upload . with huggingface_hub

.summary/0/events.out.tfevents.1677323897.groot

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:597e1ac25ad65234da8a88603b1c2e195d2b25c6753e324bcb6c8943321870ca
+size 1765278

README.md

@@ -11,16 +11,16 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: doom_health_gathering_supreme
-      type: doom_health_gathering_supreme
+      name: doom_deathmatch_bots
+      type: doom_deathmatch_bots
     metrics:
     - type: mean_reward
-      value: 14.27 +/- 5.47
+      value: 10.80 +/- 3.03
       name: mean_reward
       verified: false
 ---
 
-A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
+A(n) **APPO** model trained on the **doom_deathmatch_bots** environment.
 
 This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
 Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r eldraco/rl_course_vizdoom_
 
 To run the model after download, use the `enjoy` script corresponding to this environment:
 ```
-python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
+python -m <path.to.enjoy.module> --algo=APPO --env=doom_deathmatch_bots --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
 ```
 
 
@@ -49,7 +49,7 @@ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
 
 To continue training with this model, use the `train` script corresponding to this environment:
 ```
-python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
+python -m <path.to.train.module> --algo=APPO --env=doom_deathmatch_bots --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
 ```
 
 Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.

checkpoint_p0/best_000024416_100007936_reward_13.928.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0a58b26199fd80740a107b99de49beeb8824294c71e08138589a7bf13df06ad
+size 35139299

checkpoint_p0/checkpoint_000024100_98713600.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfa731655cf33829edc89198e08f1f2735a76ab61aa60b559a7f976beb0086a3
+size 35139859

checkpoint_p0/checkpoint_000024416_100007936.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd1382ac952fead2e1979621d988de8e491ea748262f25827ddad9018a291d05
+size 35139859

config.json

@@ -130,12 +130,12 @@
   "wide_aspect_ratio": false,
   "eval_env_frameskip": 1,
   "fps": 35,
-  "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
+  "command_line": "--env=doom_deathmatch_bots --num_workers=32 --num_envs_per_worker=24 --train_for_env_steps=100000000",
   "cli_args": {
-    "env": "doom_health_gathering_supreme",
-    "num_workers": 8,
-    "num_envs_per_worker": 4,
-    "train_for_env_steps": 4000000
+    "env": "doom_deathmatch_bots",
+    "num_workers": 32,
+    "num_envs_per_worker": 24,
+    "train_for_env_steps": 100000000
   },
   "git_hash": "unknown",
   "git_repo_name": "not a git repository"

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26aa549c10a821373437bc33149a39306ed43a3b9e8483b18369874ddd6b071b
-size 28271956
+oid sha256:d6f327390286437ef2b1c8f6c6b3e3246d0e9e9ce1a1319df4eeeafd6ffdea32
+size 134684892