Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -15.79 +/- 58.90
+      value: -52.51 +/- 78.46
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1679055653.36386f48af93.3634.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f1cff2d10b26942175f3bb9f36b155408bca0196cbf1a1a58ab2c5c68a34293
+size 1265023

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:588f3ebcc192a3211f72ff32b69b15dfb01fb1b928f21c20967447d070cf460e
+oid sha256:ebb378896b2cb4c43e971f50d7380e681cb99523b73cd341f85c99706c03d9df
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -15.787213091197373, "std_reward": 58.89675645271069, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-17T11:01:03.390607"}
+{"env_id": "LunarLander-v2", "mean_reward": -52.505278248973056, "std_reward": 78.4613331760264, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-17T12:47:52.550705"}