Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -169.67 +/- 52.28
+      value: -45.88 +/- 12.31
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 5000000
 'learning_rate': 0.00025
 'num_envs': 32
 'num_steps': 512

logs/events.out.tfevents.1699614454.e250de559c95.3617.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d7c21a6f47177f6f1ce2ebefe96754ae021026e23da9571c7945c65386f7a2
+size 1437472

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3189723ff8e0045203d1a91dabffb4c23e83cf3de915d63a3c4f8e91cc8e2ada
+oid sha256:7ddbe6a7bb7cd971cda290d314b00ff54315dbd305e34e36690c37ce7fabdb4a
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -169.67218639487047, "std_reward": 52.27977257285747, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-10T11:07:10.208675"}
+{"env_id": "LunarLander-v2", "mean_reward": -45.8794050072054, "std_reward": 12.309895691642641, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-10T12:53:08.658747"}