suveda999/ppo-LunarLander-v3

PPO LunarLander-v3

This is a Proximal Policy Optimization (PPO) agent trained using Stable-Baselines3 on the LunarLander environment.

Model Details

• Algorithm: PPO (Proximal Policy Optimization)
• Environment: LunarLander-v3
• Library: Stable-Baselines3
• Framework: PyTorch
• Task: Deep Reinforcement Learning

Evaluation Results

The trained agent was evaluated over multiple episodes.

• Mean reward: 271.62
• Standard deviation: 12.83
• Leaderboard score: 258.79

The leaderboard score is calculated as:

mean_reward - std_reward

Therefore:

271.62 - 12.83 = 258.79

Training

The model was trained using the Proximal Policy Optimization (PPO) algorithm from Stable-Baselines3.

The trained model is provided as:

ppo-LunarLander-v3.zip

Usage

You can load the trained model using Stable-Baselines3:

from stable_baselines3 import PPO

model = PPO.load("ppo-LunarLander-v3")