Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -216.18 +/- 115.42
+      value: -171.48 +/- 126.85
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 10000
-'learning_rate': 0.0001
+'learning_rate': 1e-05
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1677780524.6c4e5c51f044.16477.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c82371bb5e7b9787dbf34a71d7d9c6bd7ca4429031523acc0113b900481c8e
+size 22988

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57e56b1b19d087c6db71a56d0ddc61ec9f2715d5bbbc2fe8851c8eca39dc1a90
+oid sha256:ec2c0c01199749020f446c954ad4fe7e248e2c93c97a53a5fa9eb76c5f87afeb
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -216.17740745274355, "std_reward": 115.41958273359432, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:07:57.690611"}
+{"env_id": "LunarLander-v2", "mean_reward": -171.48233301952604, "std_reward": 126.85495305850198, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-02T18:09:00.499340"}