Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -3.57 +/- 71.35
+      value: 5.19 +/- 60.83
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 250000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1689633300.cdfd7753ad9c.30638.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:137e273ed115663b8692b478decfb7990c9970eb74df12e7106a94bed810e9b4
+size 406325

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f76c953c029480122c5a81a2516861b10770b48fee7ea05778eccfe553c84d
+oid sha256:92d292158c6ff9446de5b61c26f8d4d6880719e3c1bad85e3417de69efcbba66
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -3.5711268134092977, "std_reward": 71.34533514980963, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-17T21:51:16.322848"}
+{"env_id": "LunarLander-v2", "mean_reward": 5.1919625412988974, "std_reward": 60.82735859571718, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-17T22:40:34.701316"}