Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -29.36 +/- 32.51
+      value: 6.75 +/- 120.28
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 200000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1727341280.3332c2de52e8.12659.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91dad20ca122aaac1bfb9ace1b6c7de43a95d023d2bcb511a0fd7e7acd4deb0
+size 1255281

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ccce4430cd2484cb7e2271f5e70f49147c1e0fa609462c182399fdfbd028f05
+oid sha256:b9a2f5da9739cd080252297480009c8939101f5219045009864dcb78b9e2c213
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -29.360590076672615, "std_reward": 32.514345730352424, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T08:59:30.651254"}
+{"env_id": "LunarLander-v2", "mean_reward": 6.745036899895842, "std_reward": 120.27510527202236, "n_evaluation_episodes": 10, "eval_datetime": "2024-09-26T09:28:54.986439"}