PPO LunarLander-v3
This repository contains a Stable-Baselines3 PPO agent trained to solve the Gymnasium LunarLander environment.
Training setup
- Algorithm: PPO
- Environment: LunarLander-v3
- Policy: MlpPolicy
- Training timesteps: 1,000,000
Evaluation
The agent was evaluated on the LunarLander environment with deterministic rollout settings.
Notes
This model is intended for experimentation and educational purposes.
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
from huggingface_sb3 import load_from_hub checkpoint = load_from_hub( repo_id="Aadit-032/ppo-LunarLander-v3", filename="{MODEL FILENAME}.zip", )