DeepAI AI Chat
Log In Sign Up

Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving

by   Haochen Liu, et al.

Currently, urban autonomous driving remains challenging because of the complexity of the driving environment. Learning-based approaches, such as reinforcement learning (RL) and imitation learning (IL), have indicated superiority over rule-based approaches, showing great potential to make decisions intelligently, but they still do not work well in urban driving situations. To better tackle this problem, this paper proposes a novel learning-based method that combines deep reinforcement learning with expert demonstrations, focusing on longitudinal motion control in autonomous driving. Our proposed method employs the actor-critic structure and modifies the learning process of the policy network to incorporate both the goals of maximizing reward and imitating the expert. Moreover, an adaptive prioritized experience replay is designed to sample experience from both the agent's self-exploration and expert demonstration, so as to improve the sample efficiency. The proposed method is validated in a simulated urban roundabout scenario and compared with various prevailing RL and IL baseline approaches. The results manifest that the proposed method has a faster training speed, as well as better performance in navigating safely and efficiently.


page 1

page 3

page 4

page 5

page 8


Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving

Deep reinforcement learning (DRL) is a promising way to achieve human-li...

Learning to Drive Using Sparse Imitation Reinforcement Learning

In this paper, we propose Sparse Imitation Reinforcement Learning (SIRL)...

GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving

Deep reinforcement learning (DRL) has been demonstrated to be effective ...

RLAD: Reinforcement Learning from Pixels for Autonomous Driving in Urban Environments

Current approaches of Reinforcement Learning (RL) applied in urban Auton...

FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing

We present a system that enables an autonomous small-scale RC car to dri...

Privileged to Predicted: Towards Sensorimotor Reinforcement Learning for Urban Driving

Reinforcement Learning (RL) has the potential to surpass human performan...