Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 77.79 +/- 66.25
+      value: 216.56 +/- 77.23
       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': 1000000
 'learning_rate': 0.0025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1681760581.33ec6d47d7dd.7211.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9e56255a44f604a19f54d439557c2cd0131b9b95182e364a01cf65515e7f0be
+size 1374943

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32bde5a5a77f0301a443db06ece413b2e4526751e5a05796f4b258edd0e72ea6
+oid sha256:6effa74728beeec38da258074392d484127077d570d60b40e71b4899543777ed
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 77.78713472292023, "std_reward": 66.24713064150319, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-17T19:39:08.246053"}
+{"env_id": "LunarLander-v2", "mean_reward": 216.56424639708797, "std_reward": 77.22662197971442, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-17T20:02:07.705291"}