Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1730868355.5fc646b7334d

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426706839bcc098a4b7d8448e7396c4df39660af9db35732232c26b9eab26436
+size 1149256

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 12.51 +/- 5.76
+      value: 8.16 +/- 4.68
       name: mean_reward
       verified: false
 ---
@@ -30,7 +30,7 @@ Documentation for how to use Sample-Factory can be found at https://www.samplefa
 
 After installing Sample-Factory, download the model with:
 ```
-python -m sample_factory.huggingface.load_from_hub -r InMDev/rl_course_vizdoom_health_gathering_supreme
+python -m sample_factory.huggingface.load_from_hub -r InMDev/vizdoom_health_gathering_supreme
 ```
 
     
@@ -38,7 +38,7 @@ python -m sample_factory.huggingface.load_from_hub -r InMDev/rl_course_vizdoom_h
 
 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_health_gathering_supreme --train_dir=./train_dir --experiment=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_health_gathering_supreme --train_dir=./train_dir --experiment=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_000002215_9072640_reward_29.726.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa50dc7a06ed5bc657f809039d20c3da159a2eb46fc42022d926e33376493edc
+size 34929243

checkpoint_p0/checkpoint_000002366_9691136.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c380c016253264c91ea1ca3d02f3c2902f266ee85da97189df936a55335f0f
+size 34929669

checkpoint_p0/checkpoint_000002443_10006528.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02c76ecfb78edc1a772e78d4f2e8be48ee68bc858b4f7b1d7ced6d06bbe1231e
+size 34929669

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 4000000,
+  "train_for_env_steps": 10000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5982d7a957da62bc280e98c0313accc54f82c3241600d06d7ee87b6a8d2bde9
-size 23968635
+oid sha256:2ff44b21e88284b78b6410f0911e8519a2e81c386ee068b41bf3a6f2f05a7bbb
+size 15182217