Push agent to the Hub

README.md

@@ -17,7 +17,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 35.55 +/- 46.79
+      value: 73.47 +/- 77.72
       name: mean_reward
       verified: false
 ---
@@ -43,8 +43,8 @@ model-index:
 'num_steps': 128
 'anneal_lr': True
 'gae': True
-'gamma': 0.99
-'gae_lambda': 0.95
+'gamma': 0.999
+'gae_lambda': 0.98
 'num_minibatches': 4
 'update_epochs': 4
 'norm_adv': True

logs/events.out.tfevents.1751465629.7c6da54d0a13.19582.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aef9be7ed7ade3a6d0b914892efd2edc09cf1933c88c5dfa41e75d27336e0b8
+size 737974

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:407537f42c3f2d84a7984a8b77eaefac4b67fc8c8f348e2bd567e73394507e87
+oid sha256:95744401fcc8cfb0edb6a931f1cd983ecf9e05347bf0d7666e5d0187f6bf805d
 size 43419

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 35.54728613848199, "std_reward": 46.7925751000324, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:07:22.435266"}
+{"env_id": "LunarLander-v2", "mean_reward": 73.47403712022938, "std_reward": 77.72282262284084, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:26:22.544588"}