Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -176.31 +/- 93.42
+      value: -115.94 +/- 58.19
       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.1684215878.935e5cd9caa6.15530.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e566b8b1223616c7cfc381c16de28e1894d255e617e199122462ed777af458f0
+size 221318

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": -176.30614743256768, "std_reward": 93.42308319632728, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-16T05:35:26.369920"}
+{"env_id": "LunarLander-v2", "mean_reward": -115.9359415944134, "std_reward": 58.185936979026906, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-16T05:46:04.252897"}