Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -4.36 +/- 30.06
+      value: 44.78 +/- 51.74
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': True
 'env_id': 'LunarLander-v2'
-'total_timesteps': 500000
+'total_timesteps': 1000000
 'learning_rate': 0.0001
 'num_envs': 4
 'num_steps': 256

logs/events.out.tfevents.1690200519.b3f6f6c97ed0.16865.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d9f2d7a2deec764cbdf3474935034b22e99755f52eeb519778fa9cffeebe59
+size 933916

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d30d2732c3dec168005ea62347670f2e2c762bd43b09ae24550a9d47064ddd
+oid sha256:878085a774cf4887e4afc2d9a3e66e84f5965864f5fc6623cba6c015e13c2214
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -4.361573833537912, "std_reward": 30.057512507760382, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-24T12:08:06.826284"}
+{"env_id": "LunarLander-v2", "mean_reward": 44.784143694921895, "std_reward": 51.74095723009198, "n_evaluation_episodes": 10, "eval_datetime": "2023-07-24T12:30:29.430082"}