Traac Light Control Using Sarsa with Three State Representations

  title={Traac Light Control Using Sarsa with Three State Representations},
  author={Thomas L. Thorpe and Charles W. Anderson},
Category: Control, Navigation, and Planning: reinforcement learning. No part of this work has been submitted or appeared in other scientiic conferences. Abstract SARSA is applied to a simulated traac light control problem and compared with a xed-duration strategy and a simple, rule-based strategy. The performance of SARSA with three diierent representations of the current state of traac is analyzed. SARSA is shown to be superior to the best, xed-duration light timing and close to optimal for… CONTINUE READING
Highly Cited
This paper has 44 citations. REVIEW CITATIONS

From This Paper

Topics from this paper.


Publications citing this paper.
Showing 1-10 of 32 extracted citations

Learning Road Traffic Control : Towards Practical Traffic Control Using Policy Gradients Diplomarbeit

Silvia Richter Albert - Ludwigs - Universiẗat Freiburg Fakulẗat
View 4 Excerpts
Highly Influenced

Simulation and optimization of traffic in a city

IEEE Intelligent Vehicles Symposium, 2004 • 2004
View 5 Excerpts
Highly Influenced

Urban Traffic Signal Learning Control Using SARSA Algorithm Based on Adaptive RBF Network

2009 International Conference on Measuring Technology and Mechatronics Automation • 2009
View 7 Excerpts
Highly Influenced

Adaptive Group-Based Signal Control Using Reinforcement Learning with Eligibility Traces

2015 IEEE 18th International Conference on Intelligent Transportation Systems • 2015
View 1 Excerpt


Publications referenced by this paper.
Showing 1-6 of 6 references

A physically-realistic simulation of vehicle tra c ow

T. Thorpe
View 4 Excerpts
Highly Influenced

Denver Post, \120th is giving commuters the green

Garnaas, Steve

Fewer tra c jams thanks to computers

G. Olsson
View 2 Excerpts

A system-wide approach to adap

D. C. Chin, R. H. Smith, J. C. Spall

Similar Papers

Loading similar papers…