Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.95 +/- 84.72
+      value: -138.38 +/- 88.83
       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': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1685269716.2901d87a9fc9.8971.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5750f1209dd41516ddb4dc726610f820c92b61760dc8f57f391499fba0ac2fa
+size 221321

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:8802a401f9eedb07ef810eb6d49c91ffd77d753bd96675776004777157abd97e
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.946361618891, "std_reward": 84.71875206082076, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-28T10:25:55.823898"}
+{"env_id": "LunarLander-v2", "mean_reward": -138.37965010905629, "std_reward": 88.82898339985138, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-28T10:30:00.288550"}