Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -14.33 +/- 85.34
+      value: -59.52 +/- 15.06
       name: mean_reward
       verified: false
 ---
@@ -39,7 +39,7 @@ model-index:
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
 'learning_rate': 0.00025
-'num_envs': 4
+'num_envs': 10
 'num_steps': 128
 'anneal_lr': True
 'gae': True
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'sswt/ppo-LunarLander-v2'
-'batch_size': 512
-'minibatch_size': 128}
+'batch_size': 1280
+'minibatch_size': 320}
   ```
   

logs/events.out.tfevents.1727357800.70c6f8ef8334.11325.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18e3003432e8aaaecbdf061334bc18466f19c244b8848de2ff76986e7b16e7e9
+size 385564

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
+oid sha256:f2ac4e536be88699d71c89c91a164c3d6b446eef6fde7062a6963eebb849b80b
 size 43026

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eeafe8b577e87891549d8e3f750e79b1522e7a390630159774e95fca4603fe3
-size 195824
+oid sha256:44d1b4844e5f0de05e6adc06d5583292c8864ca765e7bf3fcd7a82ddfd456009
+size 217020

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -14.32569953203776, "std_reward": 85.34158094988845, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T13:23:15.712117"}
+{"env_id": "LunarLander-v2", "mean_reward": -59.52229243734437, "std_reward": 15.058441316149224, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T13:47:02.672185"}