Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -173.46 +/- 84.63
+      value: 37.65 +/- 71.21
       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.1682873469.86bf12937bb4.12244.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adcdd8cc9152d57b5093946fde5b95b59cd2d1f4613906805f9f00714a3ec7f3
+size 666927

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": -173.45917203991922, "std_reward": 84.62559874303895, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T16:48:45.604374"}
+{"env_id": "LunarLander-v2", "mean_reward": 37.65258087244208, "std_reward": 71.20682257855847, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-30T17:05:49.948457"}