Push agent to the Hub

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- LunarLander-v2
+- ppo
+- deep-reinforcement-learning
+- reinforcement-learning
+- custom-implementation
+- deep-rl-course
+model-index:
+- name: PPO
+  results:
+  - task:
+      type: reinforcement-learning
+      name: reinforcement-learning
+    dataset:
+      name: LunarLander-v2
+      type: LunarLander-v2
+    metrics:
+    - type: mean_reward
+      value: -141.24 +/- 69.80
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
+  

logs/events.out.tfevents.1753885576.8e26445aa2f6.68345.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d55236b15301bf8a4e52fc2bcb1233989f478062c8497198b1596dfbff6914c8
+size 109733

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d34b7ef7284ca4a960b893035438c7be3514677ec4a6b2c44cb8f0a4652cd78
+size 43419

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -141.23673282410496, "std_reward": 69.79586438215121, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-30T14:27:03.621527"}