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
- 10
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support