Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -6.92 +/- 66.76
+      value: 94.92 +/- 18.34
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 1000000
-'learning_rate': 0.0001
+'learning_rate': 0.0003
 'num_envs': 16
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1751478321.14b110196fc5.15246.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8328d9c01826d7843981f8864198818c941a5c3e37e96fa3c45d7934be66071
+size 664966

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6531bbf15b00218e3daeed917e2dffa329f40873d3905f0f4ea3cfa3515f6bcd
+oid sha256:d20506cc5fddda0a304ad4d27724638d1000095e0269af59e3d4f4ae23ab01e4
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -6.922014988267035, "std_reward": 66.7598906879058, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T17:14:46.950243"}
+{"env_id": "LunarLander-v2", "mean_reward": 94.91884535777274, "std_reward": 18.33685882372088, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T18:02:26.699585"}