Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1731062261.54cd0c9040da

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:929302b80ec8dd6692657a325d2d3c05d6c3e5a320e1c0e14835752297598de0
+size 727083

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 4.06 +/- 0.41
+      value: 11.41 +/- 4.52
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000000895_3665920_reward_23.358.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e90f42a33e006c942fb16e7ea24adb325f3843ecbfb55a8345dda3a68e7200e
+size 34929051

checkpoint_p0/checkpoint_000000910_3727360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2508e11890f5d65c94f9da1ce0ba9ed60ea7cbb7ad6496fd081359b97c4b1560
+size 34929477

checkpoint_p0/checkpoint_000000978_4005888.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa99455ba1fbe585942b03f43eed7d14008e65fbb6cd2b891c4be9c3ccb7825
+size 34929477

config.json

@@ -3,7 +3,7 @@
   "algo": "APPO",
   "env": "doom_health_gathering_supreme",
   "experiment": "default_experiment",
-  "train_dir": "/root/hfRL/ml/LunarLander-v2/train_dir",
+  "train_dir": "/content/train_dir",
   "restart_behavior": "resume",
   "device": "gpu",
   "seed": null,
@@ -16,7 +16,7 @@
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
   "num_workers": 8,
-  "num_envs_per_worker": 4,
+  "num_envs_per_worker": 16,
   "batch_size": 1024,
   "num_batches_per_epoch": 1,
   "num_epochs": 1,
@@ -130,11 +130,13 @@
   "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_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000 --learning_rate=0.0001 --batch_size=1024 --num_envs=16",
   "cli_args": {
     "env": "doom_health_gathering_supreme",
     "num_workers": 8,
-    "num_envs_per_worker": 4,
+    "num_envs_per_worker": 16,
+    "batch_size": 1024,
+    "learning_rate": 0.0001,
     "train_for_env_steps": 4000000
   },
   "git_hash": "unknown",

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf3c95fa679fc9ffc32521921710e4073367088ae805f5e334d6d5fe2e37f8d
-size 6040020
+oid sha256:f4ed78c785cd0df2285dd3f6ddb9c575870fd08a36d041831c63254bbee305ba
+size 21865704