Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -142.53 +/- 92.15
+      value: -71.53 +/- 93.58
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v2'
-'total_timesteps': 100000
+'total_timesteps': 1000000
 'learning_rate': 0.00025
 'num_envs': 4
 'num_steps': 128

logs/events.out.tfevents.1750146239.26717594ce86.10177.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228689fdcc56f408f7e920ceb085896280a30d643dca7e9712ea2bccc4500895
+size 1314038

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d044683000e9eb182c8223eb70f158316228f3d297b0325a626f4daf615756b4
+oid sha256:09ba3ff76aa6738a48e372b98069262436d0fb9781ced3ff494ac5db9ea76258
 size 43026

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": -142.52942182306936, "std_reward": 92.14563104540764, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-17T07:41:05.685006"}
+{"env_id": "LunarLander-v2", "mean_reward": -71.5275237514422, "std_reward": 93.5843440699692, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-17T08:07:24.324256"}