Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -139.95 +/- 40.61
+      value: 19.72 +/- 87.98
       name: mean_reward
       verified: false
 ---
@@ -38,9 +38,9 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 0.1
+'learning_rate': 0.0025
 'num_envs': 4
-'num_steps': 300
+'num_steps': 128
 'anneal_lr': True
 'gae': True
 'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
 'max_grad_norm': 0.5
 'target_kl': None
 'repo_id': 'caioiglesias/ppo-LunarLander-v2'
-'batch_size': 1200
-'minibatch_size': 300}
+'batch_size': 512
+'minibatch_size': 128}
   ```
   

logs/events.out.tfevents.1677779087.6c4e5c51f044.9950.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48f1b01a88cb1549f5f0e75b47ab68db0f3a5f7edfe2dde2770aff2d5aa9ce3c
+size 77388

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8400ea34a98a85e180abd047a7fe0caf8a247ee329059e8755717cdb3751fd34
+oid sha256:1130dbc2ea11f45242bc9a621ee3ac7e899b7b6bdd6c8ba053f363e2aa898e9c
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -139.95133749417, "std_reward": 40.61485880209634, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:42:32.960148"}
+{"env_id": "LunarLander-v2", "mean_reward": 19.71674801542361, "std_reward": 87.98029362693399, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T17:46:13.671541"}