Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -234.83 +/- 126.70
+      value: -166.01 +/- 122.33
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50
+'total_timesteps': 50000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1718893166.e15252c5e5f9.18564.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:466252ce1f2be1f926bcb1a44624a366c81538796207fccba177f80d3c8df91f
+size 109717

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:495bb0131c86c7648d0869f12a6f871e63f720c91b986e28dc5220939e921c48
+oid sha256:09fc1abb89be99827fdc2d651a235581a3c0f83de2d3c0dc276cdb4709b0de11
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -234.8285880290744, "std_reward": 126.69613463851499, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-20T14:18:34.843422"}
+{"env_id": "LunarLander-v2", "mean_reward": -166.0051464054959, "std_reward": 122.32876221511596, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-20T14:20:10.615176"}