modified from CleanRL

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: 261.13 +/- 28.32
+      name: mean_reward
+      verified: false
+---
+
+  # PPO Agent Playing LunarLander-v2
+
+  This is a trained model of a PPO agent playing LunarLander-v2.
+
+  # Hyperparameters
+  

model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17fc14857b5a0bbcddad1f87de7aa17a5dac2a67f9b972d28cd197e53bb75c1b
+size 42817

results.json

@@ -0,0 +1 @@
+{"env_id": "LunarLander-v2", "mean_reward": 261.1306086142445, "std_reward": 28.319145033180245, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-11T12:19:34.684977"}

rl-video-step-0.meta.json

@@ -0,0 +1 @@
+{"step_id": 0, "episode_id": 0, "content_type": "video/mp4"}