Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 53.84 +/- 114.90
+      value: 226.96 +/- 41.61
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 1000000
+'total_timesteps': 10000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1689881697.arran.609905.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be022fb31636a5adbd9ef0e47725a9f9a0a91b7a481e880095d2e17841565c80
+size 14872129

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ecc44a1453b236ef1aff6853248d1ada056628a71f58d5254c6d2d19f78b763
+oid sha256:4f4b7aab211410263272daa07e32c8884114efee73f1c82276d2e724a5291045
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 53.83939682205771, "std_reward": 114.8973949313776, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T20:33:39.591508"}
+{"env_id": "LunarLander-v2", "mean_reward": 226.96045365568108, "std_reward": 41.61089476686674, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-20T22:15:40.461019"}