Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 2.71 +/- 93.33
+      value: -89.89 +/- 34.88
       name: mean_reward
       verified: false
 ---
@@ -38,14 +38,14 @@ model-index:
 'capture_video': True
 'env_id': 'LunarLander-v2'
 'total_timesteps': 500000
-'learning_rate': 0.00025
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
 'gae_lambda': 0.95
-'num_minibatches': 16
+'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True
 'clip_coef': 0.2
@@ -56,6 +56,6 @@ model-index:
 'target_kl': None
 'repo_id': 'wilt8/ppo-CleanRL-LunarLander-v2'
 'batch_size': 512
-'minibatch_size': 32}
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1725425362.coder-william-william-gpu-dev-01-5fd55f9c84-plnfx.1477684.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c648aaa4f9984518e827c03fcc9c788d50ded9a4ae161799760a0b4c424ba37
+size 615901

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5bd38b5ca86b70ce5f3b2b2b1ff09670c6eabb43ab96819f190210b86a9177
+oid sha256:318677b220e901295b2daa123bcfbdbad8592737edace0eace892497ebef1581
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 2.714505216302001, "std_reward": 93.3328516478546, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T12:33:46.288464"}
+{"env_id": "LunarLander-v2", "mean_reward": -89.88970909595137, "std_reward": 34.881950781912344, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-04T12:58:06.316835"}