Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -229.41 +/- 120.32
+      value: 48.90 +/- 137.61
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 1000000
 'learning_rate': 0.0003
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1708898236.20b0d4113366.6506.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2edc3aa62e3252af1ee7257112c99642b3f0e36912412021465dc1d328c78613
+size 1281463

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d71f7f35ed866f10fc65b041c5f55f311f7a1fd562774bf5a85eb01941a82c9d
+oid sha256:b466a939fa9b38c745ea240f523c9658aad3e4e77f0dfad3e443a1930de1a652
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -229.41161466921147, "std_reward": 120.32376039826038, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-25T21:56:39.378705"}
+{"env_id": "LunarLander-v2", "mean_reward": 48.89713457363001, "std_reward": 137.61093299275151, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-25T22:21:11.705243"}