Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -153.92 +/- 92.17
+      value: -96.33 +/- 46.29
       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.1742499277.64eee772626b.4121.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2325de1177d7f913ed3ad5adc483276ce91efc9d55529c688c1775ad3fc5153b
+size 221309

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e592fb92948eb720ebf65e9ba651a3ca7834e96ec574ac31ef975b4528652b8
-size 42898
+oid sha256:18d7dd5e3988bbef80f64243ce6cc4003af98cb92a17fa58a0c9c43a24eda687
+size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -153.91672960586004, "std_reward": 92.16851690504303, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-20T19:20:22.936505"}
+{"env_id": "LunarLander-v2", "mean_reward": -96.33435172693163, "std_reward": 46.29036124873963, "n_evaluation_episodes": 10, "eval_datetime": "2025-03-20T19:36:00.756499"}