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: -157.55 +/- 94.87
+      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.1772438049.f791d7fac2a6.620.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3c67242789d87160a7e9d9fe6bcc0872ea19cc00f28315965f619576223e5fb
+size 221313

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:055739177b6612e8de8dd9885353e3e688725a0514366d900ccc15555262a256
+size 43419

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": -157.55203635340928, "std_reward": 94.86939205863497, "n_evaluation_episodes": 10, "eval_datetime": "2026-03-02T07:55:35.945174"}