Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -241.30 +/- 150.28
+      value: -41.43 +/- 82.99
       name: mean_reward
       verified: false
 ---
@@ -38,7 +38,7 @@ model-index:
 'capture_video': False
 'env_id': 'LunarLander-v2'
 'total_timesteps': 50000
-'learning_rate': 2.5e-05
+'learning_rate': 0.0025
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1704519361.cef9efba8278.6607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb2df34769f0cc2588e0e6c06c0444d1149f37dac0b1f52c765b51767b27f9d
+size 80028

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69749449f7aeed668bfcf9e756c7caf34decbab0fef4b633fc5164d6ec210c51
+oid sha256:fa5d3a60127dd4acfcf2b3409fdfa3b0e1badffd4f47e6f9ecb6f68272887793
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -241.30284348122964, "std_reward": 150.27613006674466, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:35:02.424957"}
+{"env_id": "LunarLander-v2", "mean_reward": -41.43157712959779, "std_reward": 82.9885349684779, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-06T05:37:07.124234"}