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: 201.90 +/- 92.46
+      value: -130.18 +/- 58.28
       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.1749659464.saracuza.73740.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1942bdfa563953a346bffad5697659b7bdf3f20c66633e87a67da6f6d31ae2b
+size 114908

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18d56e13dc90cbaa753f8878152fa034b4d39c4170d35e944e6c04b070c3c986
-size 40859
+oid sha256:e3dc4566e0324ee6708888d7a95ef488659cce6db3c8489c4e5779fc9e245e08
+size 43419

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0eb208cb474d1d1ebd30a2eda3e47bea9f347aa16101f6267e5d04ccddb2d2c
-size 19485
+oid sha256:90f0fea73b52911500ed4f9e8e8902b65e85001b3fb66018ecb64cead3c8f349
+size 24580

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 201.9, "std_reward": 92.4645337413216, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-11T12:32:49.675678"}
+{"env_id": "LunarLander-v2", "mean_reward": -130.1767910989911, "std_reward": 58.284935683058265, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-11T13:31:32.465963"}