Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -142.74 +/- 97.12
+      value: 48.84 +/- 59.25
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1682523333.cac3f3854212.40779.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62aa4f21893d32ccf4672644e9cd46c3d78d8416cb5204deb8772bab05bc33d4
+size 666919

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a363dfe098933c96feb65ea5062a91e8aacf7448c05ac211c1404fb4e0f78d9
+oid sha256:2b9d543238803c060f8dbf5c92d5a1c98334eac95137b947dc15b59717d77604
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -142.73824220448984, "std_reward": 97.11992711253414, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-26T15:32:44.986159"}
+{"env_id": "LunarLander-v2", "mean_reward": 48.83913456300335, "std_reward": 59.24940595729393, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-26T15:50:45.502038"}