Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -186.45 +/- 117.99
+      value: -118.35 +/- 55.86
       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': 1e-06
+'total_timesteps': 500000
+'learning_rate': 2.5e-06
 'num_envs': 20
 'num_steps': 128
 'anneal_lr': True

logs/events.out.tfevents.1727801701.ac0c75d0505a.458.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d66b3987c851712a306f1d80a3985e59113750e371da6459b052fd147bafd4
+size 698867

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:024652ff2483bc418d46ddae837b8c0f729cdad1ca3475f4fa66eb6fb411f261
+oid sha256:2eb32e3a8ab65e1f05b094aff72cff6b6161e876558b6b71e91eead672eb5bab
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -186.45112360699335, "std_reward": 117.98976407263036, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-01T16:53:49.271626"}
+{"env_id": "LunarLander-v2", "mean_reward": -118.3451773575317, "std_reward": 55.86093815816709, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-01T16:57:36.893193"}