Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -25.77 +/- 49.97
+      value: 20.85 +/- 60.59
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 400000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1705726258.3df18f576b92.11465.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fd731db43b02c5bd4c496b43acdff15db0e8091166c9245dc5303d3ab1cfecf
+size 552896

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccce4430cd2484cb7e2271f5e70f49147c1e0fa609462c182399fdfbd028f05
+oid sha256:e640dffe74a9c66562cb5ff289b8661fddea7e07a2b79250101af4365b9378cd
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -25.766064143671997, "std_reward": 49.967706083625046, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-20T04:49:22.330829"}
+{"env_id": "LunarLander-v2", "mean_reward": 20.84970391709787, "std_reward": 60.59235165288147, "n_evaluation_episodes": 10, "eval_datetime": "2024-01-20T05:02:28.970968"}