DriverGym: Democratising Reinforcement Learning for Autonomous Driving

Abstract

Despite promising progress in reinforcement learning (RL), developing algorithms for autonomous driving (AD) remains challenging: one of the critical issues being the absence of an open-source platform capable of training and effectively validating the RL policies on real-world data. We propose DriverGym, an open-source OpenAI Gym-compatible environment specifically tailored for developing RL algorithms for autonomous driving. DriverGym provides access to more than 1000 hours of expert logged data and also supports reactive and data-driven agent behavior. The performance of an RL policy can be easily validated on real-world data using our extensive and flexible closed-loop evaluation protocol. In this work, we also provide behavior cloning baselines using supervised learning and RL, trained in DriverGym. We make DriverGym code, as well as all the baselines publicly available to further stimulate development from the community.

Accepted to NeurIPS 2021 ML4AD Workshop

References in corpus (6)

• Playing Atari with Deep Reinforcement Learning
• Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
• CARLA: An Open Urban Driving Simulator
• One Thousand and One Hours: Self-driving Motion Prediction Dataset
• SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
• ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst