Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -124.78 +/- 89.49
+      value: -128.83 +/- 50.31
       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.1739700547.bbd3d3b79728.21657.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51d6f125c8318675e094e49fbe164081c953876e13c92f1010b323e182c8b707
+size 221316

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:339f09e8b06f686b9c10d26099e14e7a7303e9b6ecce9f9f6a67b3d5b02b6551
+oid sha256:d044683000e9eb182c8223eb70f158316228f3d297b0325a626f4daf615756b4
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -124.77710948813187, "std_reward": 89.49143198535528, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-16T10:07:51.708336"}
+{"env_id": "LunarLander-v2", "mean_reward": -128.83390465058386, "std_reward": 50.30797648643316, "n_evaluation_episodes": 10, "eval_datetime": "2025-02-16T10:10:23.721065"}