Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -235.77 +/- 92.85
+      value: -169.67 +/- 52.28
       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': 32
 'num_steps': 512

logs/events.out.tfevents.1699614300.e250de559c95.2918.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:224f0b506c9e2e1a0fc0d82bea5306227861e4165b56a30fc8745e12b1673447
+size 549724

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aff0bec92ba914a473c7ba793ff26c3a6d112ef9814908acf4c6ea8ca9e5c3a
+oid sha256:3189723ff8e0045203d1a91dabffb4c23e83cf3de915d63a3c4f8e91cc8e2ada
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -235.76969221500522, "std_reward": 92.85233607012792, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-10T11:04:36.003226"}
+{"env_id": "LunarLander-v2", "mean_reward": -169.67218639487047, "std_reward": 52.27977257285747, "n_evaluation_episodes": 10, "eval_datetime": "2023-11-10T11:07:10.208675"}