Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -191.66 +/- 83.90
+      value: 154.08 +/- 134.41
       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': 5000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1755932053.LuckyE.7652.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5da82b68ab9c705f67fc01b005cc4bda34d99476cc5b124bb22cd7602730464
+size 7057686

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bbf275af42281ac828450a52b33305f0bc1f20b2381c3deaea90b08d760f9e6
+oid sha256:57ee37f826924a8cf49ddf9e77652bb653d6bd2ddc7cdcd20a4201bf9023e344
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -191.66085888227343, "std_reward": 83.90444936186755, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-23T14:39:52.677396"}
+{"env_id": "LunarLander-v2", "mean_reward": 154.07809761055015, "std_reward": 134.40865026515365, "n_evaluation_episodes": 10, "eval_datetime": "2025-08-23T17:03:41.739859"}