Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -197.84 +/- 141.49
+      value: 20.77 +/- 54.16
       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.1707295586.9ede44d11205.9550.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0c1c1cf06043de0c0e138eff3aa430d9371ec60403ee60adfa99f7bdfe2c6e
+size 675367

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:c92c631e7b978acf25a81dd9a83a3caf08de2979f0ea9b1370f6a8fc6e2143ec
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -197.84447441927264, "std_reward": 141.48955772754826, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-07T08:45:28.779555"}
+{"env_id": "LunarLander-v2", "mean_reward": 20.76911347051417, "std_reward": 54.163830965765534, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-07T09:01:17.049529"}