Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -178.08 +/- 87.33
+      value: 3.84 +/- 136.56
       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.1680042617.bb8423eb0a97.40762.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5bf24dad3ad8f1a1b6276b089479ac97f00744b8a82a0da70a2bcc2d5656ae6
+size 665031

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc668e37d0f9ce18faff82280d7f9f830d03540d69117128d442494db1002c3
+oid sha256:63e920a347963edbe909ae7cbc29d99452527b0cb9246c9f72ae87cbbde6fdb0
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -178.0810890151037, "std_reward": 87.33375200996996, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-28T21:36:22.434626"}
+{"env_id": "LunarLander-v2", "mean_reward": 3.8396319317799823, "std_reward": 136.55944205238433, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-28T22:43:30.363688"}