Push agent to the Hub

README.md

@@ -1,6 +1,6 @@
 ---
 tags:
-- CartPole-v1
+- LunarLander-v2
 - ppo
 - deep-reinforcement-learning
 - reinforcement-learning
@@ -13,18 +13,18 @@ model-index:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
-      name: CartPole-v1
-      type: CartPole-v1
+      name: LunarLander-v2
+      type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 499.20 +/- 2.40
+      value: -41.96 +/- 18.45
       name: mean_reward
       verified: false
 ---
 
-  # PPO Agent Playing CartPole-v1
+  # PPO Agent Playing LunarLander-v2
 
-  This is a trained model of a PPO agent playing CartPole-v1.
+  This is a trained model of a PPO agent playing LunarLander-v2.
 
   # Hyperparameters
   

logs/events.out.tfevents.1748165876.6d34a00c6b9b.1194.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de23eba5664301335b22de55daa83c642be857ce94e3fdf4e45e6c20c1e1842b
+size 542579

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0d90448daca90d9e08942ca75d769d8e2545721b1f1ebd1e593348197fb6ba6
-size 40859
+oid sha256:00675ea7e29b67398165c48dd22229d16106d928d5efe9e3a33d47f9c2766e89
+size 43419

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18770d704d189e2699894ae6869c3a54f00dd0915f857cae55d4c2bab98d7782
-size 50945
+oid sha256:e849789205bf0ed5115977704c2b8c0ca1f164ad0fd91226d25e6545d9a72822
+size 226065

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 499.2, "std_reward": 2.4, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-25T09:28:23.609401"}
+{"env_id": "LunarLander-v2", "mean_reward": -41.961003549080786, "std_reward": 18.453073618149013, "n_evaluation_episodes": 10, "eval_datetime": "2025-05-25T09:59:22.336986"}