Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -175.49 +/- 117.96
+      value: -159.46 +/- 97.40
       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': 0.001
 'num_envs': 4
 'num_steps': 1024
 'anneal_lr': True

logs/events.out.tfevents.1691959543.bcadd1928d08.11786.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5700d0c3975e2a5334674aec3983a97283d12615bf80dc8dccf3ab0f2027cb33
+size 11861

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cbab9c63d0d05e44a36044bc75f5bf8f6d43380e888066e4128f66e25a752b0
+oid sha256:01cb2c7deeba9912724733e05c9e07552cbf46a08cc97798d378b8339ee09448
 size 4285797

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -175.48532932864288, "std_reward": 117.96010241402351, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:45:07.065148"}
+{"env_id": "LunarLander-v2", "mean_reward": -159.46132372221183, "std_reward": 97.3977647762934, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-13T20:45:57.957686"}