Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -143.67 +/- 104.33
+      value: -216.69 +/- 158.86
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 200000
 'learning_rate': 5e-05
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1714950057.71d3fa3d3a00.22952.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:216b8c8062c2a80bccec6fa3bd99528f990e15424fd2fed8b237166d7fa706a2
+size 434817

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc4440e4d2e67eb34e3fef5529889e2aee114264c46167d6bb5ee4e2198c7521
+oid sha256:40ed3275aca4f788ce69c0d379c65c7c6ff2213350df2206855a0b2543b74308
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -143.66767441508628, "std_reward": 104.33212867200926, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T23:00:06.128740"}
+{"env_id": "LunarLander-v2", "mean_reward": -216.68981261719736, "std_reward": 158.85547555031908, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T23:03:41.803529"}