Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -21.33 +/- 99.79
+      value: 150.87 +/- 123.22
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.00025
+'learning_rate': 0.001
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1710255572.28d9d214646f.25284.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c16afd5ee51efcec992ed2d6de892d0350610ebf542ddd5fc8e23f2efc6dd68
+size 1318484

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
+oid sha256:3de01bf119eba146ac24541cba34cb0131b1b8bf34d28122ae0b978abbe96bd0
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -21.329722121677865, "std_reward": 99.78723898164773, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-12T14:56:50.973649"}
+{"env_id": "LunarLander-v2", "mean_reward": 150.87450746432933, "std_reward": 123.22120469166885, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-12T15:20:04.623096"}