Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -157.01 +/- 108.84
+      value: -50.60 +/- 98.93
       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': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1758852567.d0349b3599e9.8882.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47f8d8db0b52fd02d485f03951f27dcc0bfe5e742cf6607da0f86f1e50c8048f
+size 1314045

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d14e1fa1c82b746371962c297adde52d67743c8fa97fc1a968fb5acee2e42fa1
+oid sha256:93c6be18222ddcf0d0ce81a25ce60a0d61fb96cb53a54bd3c8ad07630dd2bf80
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -157.00958358343237, "std_reward": 108.84228513395296, "n_evaluation_episodes": 10, "eval_datetime": "2025-09-26T02:05:35.651101"}
+{"env_id": "LunarLander-v2", "mean_reward": -50.59565654260231, "std_reward": 98.93225406999025, "n_evaluation_episodes": 10, "eval_datetime": "2025-09-26T02:39:22.331211"}