A Mean-variance Optimization DQN in Autonomous Driving

Zhizhong Zhao, Ruoyu Sun

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review


Deep reinforcement learning is a popular and effective approach for autonomous driving to achieve safe and complex self-driving with little or no human input. However, in the random and intricate driving scenarios with surrounding traffic, conventional RL-algorithms based on greedy policy might be unstable and inefficient in training because of their lack in risk sensitivity. This paper proposes an RL-learning approach for autonomous driving which includes the estimation of expected cumulative future reward and its standard deviation. We utilize the difference between expectation and standard deviation as the decision foundation to improve the risk sensitivity of policy and training performance. The proposed algorithm is implemented in the CARLA simulation environment and the results demonstrate that vehicle agent based on our learning algorithm is able to learn more efficiently and drive more safely.
Original languageEnglish
Title of host publicationCMAAE 2021: 2021 International Conference on Mechanical, Aerospace and Automotive Engineering
Number of pages6
Publication statusPublished - 7 Jun 2022


Dive into the research topics of 'A Mean-variance Optimization DQN in Autonomous Driving'. Together they form a unique fingerprint.

Cite this