Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -183.00 +/- 125.51
+      value: -3.57 +/- 71.35
       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': 4
 'num_steps': 128

logs/events.out.tfevents.1689629738.cdfd7753ad9c.15770.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01bb231ff100a1f685c0e79859bdc5aaa4f1ba4cd5d1d3236accfcc598a85890
+size 675621

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c706c81696f37ceaeb74d41e1262ec54c4e2f63b8cbb791c8b01decf796f6a53
+oid sha256:69f76c953c029480122c5a81a2516861b10770b48fee7ea05778eccfe553c84d
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -182.9981924347296, "std_reward": 125.51402426218463, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-17T21:35:00.977112"}
+{"env_id": "LunarLander-v2", "mean_reward": -3.5711268134092977, "std_reward": 71.34533514980963, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-17T21:51:16.322848"}