Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -146.43 +/- 80.84
+      value: -142.58 +/- 63.60
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 100000
-'learning_rate': 0.00025
+'learning_rate': 2.5e-05
 'num_envs': 12
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1676773335.5e7fcccfc678.4163.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ed19b0d31a111dbc6f01a2aea8e2540d30258b73b4015dfaa102ce01f54a20
+size 159119

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f55232df2858b3ad124e54f9f00fc1eeb7d7b3d2de2e5502556732d34abb04f
+oid sha256:ec50c094714203054e4da9f0499b48c992eb2cbabc15dcee46ddaac3b56d34af
 size 42597

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -146.42941391405682, "std_reward": 80.8434225716326, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:21:06.101440"}
+{"env_id": "LunarLander-v2", "mean_reward": -142.57921862519373, "std_reward": 63.604505800627514, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-19T02:23:02.320757"}