Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -218.70 +/- 92.08
+      value: -30.31 +/- 63.48
       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': 7e-05
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1714948103.71d3fa3d3a00.14480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ee10ac8878c9ad672d6657946c7587f29c4ab3cf4eafe8391eb68e7b6968d3f
+size 840036

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bb910849e57096a8ff50cb41728e1dd055fc2dec961eacf8724b1216e2d4b36
+oid sha256:257dce014a420a9aad7dee8211a89ba054130a44f4ea30c8a492c48130956578
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -218.70326690099583, "std_reward": 92.08052157290372, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:26:51.013601"}
+{"env_id": "LunarLander-v2", "mean_reward": -30.310759067823096, "std_reward": 63.483640716729155, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-05T22:37:03.088230"}