Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 7.75 +/- 62.33
+      value: -97.53 +/- 75.44
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.001
+'learning_rate': 0.0009
 'num_envs': 5
-'num_steps': 32
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.999
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'Katelie/lunarlander-cleanrl-ppo'
-'batch_size': 160
-'minibatch_size': 40}
+'batch_size': 640
+'minibatch_size': 160}
   ```
   

logs/events.out.tfevents.1707495965.a74decb87bc7.15433.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:787c50d30499638522bcb8011ff3dcd45dbea3b7c75d473adea96de79b9b39cf
+size 98762

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ff82754a85d15c498a569551fe1a8d90abd181bfe4517a250a84e4752ba03cb
+oid sha256:059db6360f0496730e19f4d1548d168f0a2eaee555588c3c3012eaed193211ae
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 7.748542567052427, "std_reward": 62.32522965883734, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T16:06:32.290066"}
+{"env_id": "LunarLander-v2", "mean_reward": -97.53308123478777, "std_reward": 75.4442992353469, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T16:26:45.583814"}