Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -166.78 +/- 74.51
+      value: -136.97 +/- 69.86
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 50000
+'total_timesteps': 100000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1749893118.920a0af454e3.8218.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8053651ee407b9c3d0aceeefb5c6375b73da48889cc13ec680431f4561658b85
+size 221317

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
+oid sha256:18d7dd5e3988bbef80f64243ce6cc4003af98cb92a17fa58a0c9c43a24eda687
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -166.77981593381455, "std_reward": 74.51167460668584, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-14T09:22:18.205078"}
+{"env_id": "LunarLander-v2", "mean_reward": -136.9724835718837, "std_reward": 69.86408592817858, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-14T09:26:41.451858"}