Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1722095075.ef7d0302e262

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bacca8b88c23f8e0a24afa86fef5b0ad7198ef30d51db5ae0479af7700cd74d
+size 973823

.summary/0/events.out.tfevents.1722098468.ef7d0302e262

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eaaa95e475fb79504804251337f1e9de373defede4188837977b25069e9ca8b
+size 2683

.summary/0/events.out.tfevents.1722099573.ef7d0302e262

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55122ce63e63c5a6240126ea17a98a710d3f14e9c27795a912d9d0bd249cfd48
+size 4532

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 9.49 +/- 5.36
+      value: 11.08 +/- 5.57
       name: mean_reward
       verified: false
 ---
@@ -38,19 +38,19 @@ python -m sample_factory.huggingface.load_from_hub -r bakermann/rl_course_vizdoo
 
 To run the model after download, use the `enjoy` script corresponding to this environment:
 ```
-python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --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=rl_course_vizdoom_health_gathering_supreme
 ```
 
 
 You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
 See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
-        
+    
 ## Training with this model
 
 To continue training with this model, use the `train` script corresponding to this environment:
 ```
-python -m .usr.local.lib.python3.10.dist-packages.colab_kernel_launcher --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=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_000000978_4005888_reward_26.710.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b66a25d4ee4002cd227674ff614102274f77e0317acf6732cf305aa8d6ff4f5f
+size 34929051

checkpoint_p0/checkpoint_000000980_4014080.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:819d32b0c78c0b04fdbf86c260354e2eb0b8ac10bcee41ade8dadab7c147a3dc
+size 34929669

checkpoint_p0/checkpoint_000000982_4022272.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06d9a91d27207b4202009d7fd530b6deab91e72908b1b35428b38339283b56bf
+size 34929220

config.json

@@ -46,6 +46,8 @@
   "learning_rate": 0.0001,
   "lr_schedule": "constant",
   "lr_schedule_kl_threshold": 0.008,
+  "lr_adaptive_min": 1e-06,
+  "lr_adaptive_max": 0.01,
   "obs_subtract_mean": 0.0,
   "obs_scale": 255.0,
   "normalize_input": true,
@@ -136,6 +138,5 @@
     "train_for_env_steps": 4000000
   },
   "git_hash": "unknown",
-  "git_repo_name": "not a git repository",
-  "train_script": ".usr.local.lib.python3.10.dist-packages.colab_kernel_launcher"
+  "git_repo_name": "not a git repository"
 }

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66820dfd95fc556f2f5275f528b2192bf80fcc6be93b0c079e4f0c7c078320f1
-size 17427903
+oid sha256:f880ff2a9044c183b1b7024e206295221f2657969dbe05ea9a0ef7a3ea611e14
+size 21318405