Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -40.06 +/- 17.48
+      value: 256.95 +/- 14.74
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
-'learning_rate': 0.0001
+'total_timesteps': 10000000
+'learning_rate': 0.0003
 'num_envs': 8
 'num_steps': 256
 'anneal_lr': True

logs/events.out.tfevents.1736185101.arbocensus-ASUS-TUF-Dash-F15-FX516PC-FX516PC.31206.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db3ce46df562a675aacfa190b50eef9c427368ba232fe6d5208633f137b4f441
+size 6929837

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f34ec63e310e4785fd5bfd91325c070945adf7450bfc88d9eb19f09c300f81e
+oid sha256:450944513726bf21a5d373756513c19b73a52bae1db5d2795c7046aa6a964627
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -40.05541247869074, "std_reward": 17.479252215560937, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-06T14:30:46.150511"}
+{"env_id": "LunarLander-v2", "mean_reward": 256.95458609195856, "std_reward": 14.735551572508728, "n_evaluation_episodes": 10, "eval_datetime": "2025-01-06T15:52:36.685006"}