Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -166.71 +/- 92.60
+      value: 268.97 +/- 35.91
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 10000
+'total_timesteps': 2000000
 'learning_rate': 0.00025
 'num_envs': 32
 'num_steps': 256

logs/events.out.tfevents.1733218236.c20003bcb990.32868.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43923e0f0399908d8b4ce876d7921f18c5ec00fac7e3c58fd79e361c2523a15f
+size 812214

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00c8db538eaf45023fda6c19f8d1734b432386e07c46552ff10d284493f6a84c
+oid sha256:6aff11edd6cb849747f1345bc5ea632430b4c7d415bc5ebf764244861624fc4f
 size 59774

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -166.7136352555106, "std_reward": 92.59981937087012, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T09:30:14.839245"}
+{"env_id": "LunarLander-v2", "mean_reward": 268.96683967903965, "std_reward": 35.9052026725538, "n_evaluation_episodes": 10, "eval_datetime": "2024-12-03T10:13:52.346200"}