Skip to main content

Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning

Publication ,  Journal Article
Bozkurt, AK; Wang, Y; Zavlanos, MM; Pajic, M
Published in: Proceedings - IEEE International Conference on Robotics and Automation
May 1, 2020

We present a reinforcement learning (RL) frame-work to synthesize a control policy from a given linear temporal logic (LTL) specification in an unknown stochastic environment that can be modeled as a Markov Decision Process (MDP). Specifically, we learn a policy that maximizes the probability of satisfying the LTL formula without learning the transition probabilities. We introduce a novel rewarding and discounting mechanism based on the LTL formula such that (i) an optimal policy maximizing the total discounted reward effectively maximizes the probabilities of satisfying LTL objectives, and (ii) a model-free RL algorithm using these rewards and discount factors is guaranteed to converge to such a policy. Finally, we illustrate the applicability of our RL-based synthesis approach on two motion planning case studies.

Duke Scholars

Published In

Proceedings - IEEE International Conference on Robotics and Automation

DOI

ISSN

1050-4729

Publication Date

May 1, 2020

Start / End Page

10349 / 10355
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Bozkurt, A. K., Wang, Y., Zavlanos, M. M., & Pajic, M. (2020). Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning. Proceedings - IEEE International Conference on Robotics and Automation, 10349–10355. https://doi.org/10.1109/ICRA40945.2020.9196796
Bozkurt, A. K., Y. Wang, M. M. Zavlanos, and M. Pajic. “Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning.” Proceedings - IEEE International Conference on Robotics and Automation, May 1, 2020, 10349–55. https://doi.org/10.1109/ICRA40945.2020.9196796.
Bozkurt AK, Wang Y, Zavlanos MM, Pajic M. Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning. Proceedings - IEEE International Conference on Robotics and Automation. 2020 May 1;10349–55.
Bozkurt, A. K., et al. “Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning.” Proceedings - IEEE International Conference on Robotics and Automation, May 2020, pp. 10349–55. Scopus, doi:10.1109/ICRA40945.2020.9196796.
Bozkurt AK, Wang Y, Zavlanos MM, Pajic M. Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning. Proceedings - IEEE International Conference on Robotics and Automation. 2020 May 1;10349–10355.

Published In

Proceedings - IEEE International Conference on Robotics and Automation

DOI

ISSN

1050-4729

Publication Date

May 1, 2020

Start / End Page

10349 / 10355