Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -157.84 +/- 137.00
+      value: -10.25 +/- 58.68
       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.1693297941.7c4920e5d209.4349.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd84f676a74a728bcad31a722bf1441b18d11f33d15c0ddde5b42103234c2ba5
+size 675240

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ba9eba95178b8c1eeff91f1866f65cb2c8b1c65ceedc704e4da139555fb0614
+oid sha256:95d2db815a33646e84e478628a4da4f156c95480a7b55276eebdc219ec4fcd18
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -157.83642669583395, "std_reward": 137.00198967567397, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-29T08:31:07.594639"}
+{"env_id": "LunarLander-v2", "mean_reward": -10.248815162729326, "std_reward": 58.68009718401322, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-29T08:46:29.421813"}