Reinforcement Learning with Uncertainty Estimation for Tactical Decision-Making in Intersections
Paper in proceedings, 2020

This paper investigates how a Bayesian reinforcement learning method can be used to create a tactical decision-making agent for autonomous driving in an intersection scenario, where the agent can estimate the confidence of its decisions. An ensemble of neural networks, with additional randomized prior functions (RPF), are trained by using a bootstrapped experience replay memory. The coefficient of variation in the estimated Q-values of the ensemble members is used to approximate the uncertainty, and a criterion that determines if the agent is sufficiently confident to make a particular decision is introduced. The performance of the ensemble RPF method is evaluated in an intersection scenario and compared to a standard Deep Q-Network method, which does not estimate the uncertainty. It is shown that the trained ensemble RPF agent can detect cases with high uncertainty, both in situations that are far from the training distribution, and in situations that seldom occur within the training distribution. This work demonstrates one possible application of such a confidence estimate, by using this information to choose safe actions in unknown situations, which removes all collisions from within the training distribution, and most collisions outside of the distribution.


Carl-Johan E Hoel

Volvo Group

AI Sweden

Chalmers, Mechanics and Maritime Sciences, Vehicle Engineering and Autonomous Systems

Tommy Tram

Chalmers, Electrical Engineering, Systems and control, Mechatronics

Zenuity AB

AI Sweden

Jonas Sjöberg

Chalmers, Electrical Engineering, Systems and control, Mechatronics

IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC


2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)
Rhodes, Greece,

WASP SAS: Summaries and data-structures for continuous data processing and analysis systems

Wallenberg AI, Autonomous Systems and Software Program, 2018-01-01 -- 2023-01-01.

Areas of Advance


Subject Categories

Electrical Engineering, Electronic Engineering, Information Engineering

Probability Theory and Statistics

Computer Systems



More information

Latest update

2/3/2021 7