Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 252.45 +/- 38.21
+      value: 280.55 +/- 20.38
       name: mean_reward
       verified: false
 ---
@@ -30,15 +30,15 @@ model-index:
   ```python
   {'env_id': 'LunarLander-v2'
 'learning_rate': 0.0007
-'gamma': 0.999
-'gae_lambda': 0.92
-'clip_coef': 0.32
-'total_timesteps': 5000000
+'gamma': 0.98
+'gae_lambda': 0.95
+'clip_coef': 0.2
+'total_timesteps': 50000000
 'ent_coef': 0.01
-'vf_coef': 0.621
-'max_grad_norm': 0.72
-'epsilon': 0.02
-'num_minibatches': 16
+'vf_coef': 0.5
+'max_grad_norm': 0.5
+'epsilon': 0.01
+'num_minibatches': 4
 'update_epochs': 4}
   ```
   

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e92f586866634941718b53c161efe584efc960195336ae23c4d0d94c552297f
-size 102742
+oid sha256:79caddf97e7d4f9a6cbf8198c2f2d186aea657048a8972bcbd5692b89c5d67a5
+size 129902

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 252.44526541210985, "std_reward": 38.21408993653363, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-16T14:14:56.925260"}
+{"env_id": "LunarLander-v2", "mean_reward": 280.5464417114993, "std_reward": 20.378438258144776, "n_evaluation_episodes": 10, "eval_datetime": "2024-07-17T00:20:25.351131"}