Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -29.00 +/- 34.39
+      value: 12.11 +/- 78.68
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1735412494.2763f7ab14bb.12267.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8774d96515bf327361ae671d0b2400db5b4ef47ecc9fb8cb840ae99b75b0301f
+size 1255270

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccce4430cd2484cb7e2271f5e70f49147c1e0fa609462c182399fdfbd028f05
+oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -28.995675383970166, "std_reward": 34.38629337148058, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T19:00:26.799570"}
+{"env_id": "LunarLander-v2", "mean_reward": 12.11017751697826, "std_reward": 78.67787634325737, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-28T19:29:49.930211"}