Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -177.20 +/- 110.37
+      value: -133.59 +/- 61.55
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 500000
 'learning_rate': 0.00025
 'num_envs': 8
 'num_steps': 512

logs/events.out.tfevents.1690198391.b3f6f6c97ed0.7361.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddf9ea5f4af670f504c721e66f7e0dff14be4c2b983433c6a586bf8fcecaf22
+size 548055

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bebfba309dd5d2cc797f8fda8852f21f69e0bdacd64cdf748c24647e0e4d727
+oid sha256:2b78a7312cd50eaf07357bde5d7c0904b0966adf2288b3613fdf725bf2e00480
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -177.1957138120413, "std_reward": 110.3713200862474, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-24T11:32:08.766942"}
+{"env_id": "LunarLander-v2", "mean_reward": -133.59093298874228, "std_reward": 61.5549071813801, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-24T11:37:23.243509"}