manojdokala/unit8-ppo-LunarLander-v2

PPO Agent playing LunarLander-v2 (Unit 8 Part 1)

This is a trained model of a PPO agent playing LunarLander-v2 for Unit 8 Part 1 of the Hugging Face Deep Reinforcement Learning Course.

Evaluation Results

• Mean Reward: 290.85 +/- 20.01
• Environment: LunarLander-v2
• Algorithm: PPO (Proximal Policy Optimization)

Usage

To use this model in your RL pipeline:

from stable_baselines3 import PPO
from huggingface_sb3 import load_from_hub

model = load_from_hub(
    repo_id="manojdokala/ppo-LunarLander-v2-unit8",
    filename="PPO-LunarLander-v2.zip"
)