Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -164.16 +/- 133.60
+      value: -127.93 +/- 86.57
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 1e-05
+'learning_rate': 1.5e-05
 'num_envs': 6
 'num_steps': 256
 'anneal_lr': True

logs/events.out.tfevents.1746578280.b45e59692ef7.15307.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01a7607bc3fc731f8e2bab83ce702da9e51089c5731153d30e166371ef4cfd70
+size 80660

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c26ca2694858cbb4980422aa51ff580eb35af0a2b11b10ab0dd41fc5c83ae6b3
+oid sha256:64ce3d8291cb958b4b58580f27c404db6ee56893368457e61bc5d4cc3c1cd2b3
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -164.15516410785298, "std_reward": 133.6040180852962, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:36:53.684223"}
+{"env_id": "LunarLander-v2", "mean_reward": -127.93070919552201, "std_reward": 86.57261284016951, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-07T00:38:30.149708"}