DriverGym: Democratising Reinforcement Learning for Autonomous Driving

11/12/2021
by   Parth Kothari, et al.
11

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.

READ FULL TEXT

page 1

page 6

research
01/29/2022

ApolloRL: a Reinforcement Learning Platform for Autonomous Driving

We introduce ApolloRL, an open platform for research in reinforcement le...
research
11/14/2022

NeurIPS 2022 Competition: Driving SMARTS

Driving SMARTS is a regular competition designed to tackle problems caus...
research
07/23/2022

Driver Dojo: A Benchmark for Generalizable Reinforcement Learning for Autonomous Driving

Reinforcement learning (RL) has shown to reach super human-level perform...
research
11/01/2018

Horizon: Facebook's Open Source Applied Reinforcement Learning Platform

In this paper we present Horizon, Facebook's open source applied reinfor...
research
10/25/2022

Sim-to-Real via Sim-to-Seg: End-to-end Off-road Autonomous Driving Without Real Data

Autonomous driving is complex, requiring sophisticated 3D scene understa...
research
10/13/2021

Offline Reinforcement Learning for Autonomous Driving with Safety and Exploration Enhancement

Reinforcement learning (RL) is a powerful data-driven control method tha...
research
06/27/2023

Rethinking Closed-loop Training for Autonomous Driving

Recent advances in high-fidelity simulators have enabled closed-loop tra...

Please sign up or login with your details

Forgot password? Click here to reset