Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -44.52 +/- 85.75
+      value: 206.64 +/- 107.48
       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': 500000
 'learning_rate': 0.00025
 'num_envs': 6
 'num_steps': 128

logs/events.out.tfevents.1714309923.4f7e93093a7f.3836.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c01b8600b5541581094ec9cdfb38ff41865f810470a1d05f3bf36fe57ef3b25
+size 521027

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5687ee1d5c8d4748077b77ff955ceb0049782356e3dfe1f7727361f26661d7c1
+oid sha256:06fbc068a674522bc781fcdc27099f11145a8aa780ef172b86cbaab15446cbf8
 size 42898

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -44.515785329977845, "std_reward": 85.7539446390707, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-28T13:09:26.068668"}
+{"env_id": "LunarLander-v2", "mean_reward": 206.6385907506272, "std_reward": 107.48165085760571, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-28T13:25:12.858891"}