Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -24.70 +/- 52.00
+      value: 6.03 +/- 78.05
       name: mean_reward
       verified: false
 ---
@@ -40,12 +40,12 @@ model-index:
 'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 16
-'num_steps': 128
+'num_steps': 1024
 'anneal_lr': True
 'gae': True
 'gamma': 0.9995
 'gae_lambda': 0.97
-'num_minibatches': 4
+'num_minibatches': 64
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'grib0ed0v/ppo-LunarLander-v2-unit8'
-'batch_size': 2048
-'minibatch_size': 512}
+'batch_size': 16384
+'minibatch_size': 256}
   ```
   

logs/events.out.tfevents.1728032290.32e588a9c7ee.16910.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:582d28c9d2af98484aa6472c00610e31196680ab2b1834d65a45a93dc42fac3a
+size 239948

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce9fe69889acbcf8344df8324cf4aa1545cd56fc8766b3883529cb2f2613e955
+oid sha256:12d5c83ba110110849ec52ef8cc49dd476dc2ae349e33dc4f35c61f69d3f3f63
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -24.6983643934922, "std_reward": 52.00093006149238, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-04T08:56:25.536757"}
+{"env_id": "LunarLander-v2", "mean_reward": 6.029210496709192, "std_reward": 78.04807198260976, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-04T09:06:27.688221"}