Learning to Drive using Inverse Reinforcement Learning and Deep Q-Networks

Abstract

We propose an inverse reinforcement learning (IRL) approach using Deep Q-Networks to extract the rewards in problems with large state spaces. We evaluate the performance of this approach in a simulation-based autonomous driving scenario. Our results resemble the intuitive relation between the reward function and readings of distance sensors mounted at different poses on the car. We also show that, after a few learning rounds, our simulated agent generates collision-free motions and performs human-like lane change behaviour.

NIPS workshop on Deep Learning for Action and Interaction, 2016

References in corpus (2)

• End to End Learning for Self-Driving Cars
• Maximum Entropy Deep Inverse Reinforcement Learning

Cited by in corpus (10)

• A Survey of Deep RL and IL for Autonomous Driving Policy Learning
• Deep Reinforcement Learning for Autonomous Driving
• MADRaS : Multi Agent Driving Simulator
• Deep Reinforcement Learning and Transportation Research: A Comprehensive Review
• Parameter Sharing Reinforcement Learning Architecture for Multi Agent Driving Behaviors
• Decentralized Cooperative Lane Changing at Freeway Weaving Areas Using Multi-Agent Deep Reinforcement Learning
• Reinforcement Learning Based Safe Decision Making for Highway Autonomous Driving
• Regularized Inverse Reinforcement Learning
• Learning to drive via Apprenticeship Learning and Deep Reinforcement Learning
• A Generalised Inverse Reinforcement Learning Framework