Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -33.39 +/- 104.57
+      value: 185.90 +/- 102.99
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 250000
+'total_timesteps': 10000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1692228261.muon.35006.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34377e21c42fe07ec2abec1c438b9fba62be25d9731e4c9fa3478bd5bc26c050
+size 15036180

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6378b0a23fc1f9aec48007f8f0d51050275f7d483823be9704520470d35c89
+oid sha256:2b8e1483845d46f5eeeca4350da0c655ef791ad3492cc3b85efe563f1fddee1e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -33.39256132611031, "std_reward": 104.56894642195252, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T16:17:24.815375"}
+{"env_id": "LunarLander-v2", "mean_reward": 185.89920698828374, "std_reward": 102.98591994480977, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-16T17:22:57.588901"}