Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -140.61 +/- 118.71
+      value: -165.43 +/- 163.16
       name: mean_reward
       verified: false
 ---
@@ -37,8 +37,8 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
-'learning_rate': 0.00025
+'total_timesteps': 100000
+'learning_rate': 0.0002
 'num_envs': 4
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1732731053.45d7fe83a2d9.3824.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8752a87e8cba268258ba4874d55e7cb5404782158ceaebcf84ff662ce78c88a4
+size 212783

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:d99c0eb6374547625d93179ea9efdd4b688ff49f7928d77111ddc1c81848201d
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -140.61137478525967, "std_reward": 118.71127676008234, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-27T18:09:29.136862"}
+{"env_id": "LunarLander-v2", "mean_reward": -165.4327028025198, "std_reward": 163.16202385339415, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-27T18:12:20.637696"}