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

2016/12/12 by Sahand Sharifzadeh, Sharifzadeh, Sahand, Ioannis Chiotellis +5 · 3 citations
Computer Science · Engineering · Neuroscience · #Artificial Intelligence (cs.AI) #Autonomous Vehicle Technology and Safety #EEG and Brain-Computer Interfaces #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.1612.03653

openalex publication_date 2016/12/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• End to End Learning for Self-Driving Cars

Cited by

• A Generalised Inverse Reinforcement Learning Framework
• Learning to drive via Apprenticeship Learning and Deep Reinforcement Learning
• Deep Reinforcement Learning for Autonomous Driving

Related

• Simulated Autonomous Driving in a Realistic Driving Environment using Deep Reinforcement Learning and a Deterministic Finite State Machine
• Automated Driving Maneuvers under Interactive Environment based on Deep Reinforcement Learning
• End-to-End Deep Reinforcement Learning for Lane Keeping Assist
• Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving
• An Independent Study of Reinforcement Learning and Autonomous Driving