← Return to projects

project

2D Autonomous Driving

A reinforcement-learning comparison of PPO, A2C, and QRDQN agents trained to navigate simulated highway and merge environments.

01
research
02
Researcher and Developer
03
Python / PyTorch / Stable-Baselines3 / Highway-Env / TensorBoard / BoTorch

2D Autonomous Driving compares PPO, A2C, and QRDQN reinforcement-learning agents trained and evaluated in simulated highway and merge environments.

The repository includes configurable training and evaluation scripts, TensorBoard monitoring, Bayesian hyperparameter optimization, saved model artifacts, best-parameter configurations, and exported average reward summaries.

Draft status

Full write-up in progress. This page currently summarizes the repository-backed project record.