Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v3
     metrics:
     - type: mean_reward
-      value: 68.14 +/- 87.81
+      value: 244.43 +/- 40.22
       name: mean_reward
       verified: false
 ---
@@ -37,7 +37,7 @@ model-index:
 'wandb_entity': None
 'capture_video': False
 'env_id': 'LunarLander-v3'
-'total_timesteps': 1000000
+'total_timesteps': 3000000
 'learning_rate': 0.0003
 'num_envs': 16
 'num_steps': 256

logs/events.out.tfevents.1771625716.744ac6b21567.19032.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77ab13fc4b25f33143ce3c8641eb34b9a6d60f6fe1893b6ea5a5b70a289435c9
+size 379673

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44995b5483c42d507c70646f326df2f5d595f87eee62f06b215ed8111235b62c
+oid sha256:4ca6ed3dda4b8c197e5be419445e293cf237ad1efb6bf81534b93acec1b60396
 size 43419

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:192aacf20a4581bc36a166888e73fdae4e4fad9f5938107d3650f11c8f53b7b2
-size 168398
+oid sha256:3033fe11767c38f42fc675fde90dd6cb5327d34988b408ebc6c2cbaa1165c211
+size 116409

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v3", "mean_reward": 68.1433781593476, "std_reward": 87.8130300295231, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-20T22:12:30.891299"}
+{"env_id": "LunarLander-v3", "mean_reward": 244.42973315604976, "std_reward": 40.218979831683036, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-20T22:29:33.693569"}