This repository contains the implementation of Proximal Policy Optimization (PPO) algorithm applied on the highway environment, using both discrete and continuous action spaces.
The goal of this project is to implement the PPO algorithm on a highway environment and compare the performance of the algorithm with discrete and continuous action spaces. The highway environment is a classic problem in the field of reinforcement learning, where an agent learns to navigate a car on a highway and avoid collisions with other vehicles.
To run this project, you will need to have the following installed on your system:
- Python 3.6 or higher
- OpenAI Gym
- Jax
- Rlax
- Distrax
Contributions are welcome! Please feel free to submit a pull request or raise an issue.
This project is licensed under the MIT License.