IROS 2015 Paper Abstract

Close

Paper ThCT5.4

Wen, Min (University of Pennsylvania), Ehlers, Ruediger (University of Bremen), Topcu, Ufuk (University of Pennsylvania)

Correct-By-Synthesis Reinforcement Learning with Temporal Logic Constraints

Scheduled for presentation during the Regular session "Reactive and Sensor-Based Planning" (ThCT5), Thursday, October 1, 2015, 12:05−12:20, Saal A3

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems, Sept 28 - Oct 03, 2015, Congress Center Hamburg, Hamburg, Germany

This information is tentative and subject to change. Compiled on July 20, 2019

Keywords Reactive and Sensor-Based Planning, Formal Methods in Robotics and Automation, Robot Reinforcement Learning

Abstract

We consider a problem on the synthesis of optimal reactive controllers with an a priori unknown performance criterion while satisfying a given temporal logic specification through the interaction with an uncontrolled environment. We decouple the problem into two sub-problems. First, we extract a (maximally) permissive strategy for the system, which encodes multiple (possibly all) ways in which the system can react to the adversarial environment and satisfy the specifications. Then, we quantify the a priori unknown performance criterion as a (still unknown) reward function, and compute -- by using the so-called maximin-Q learning algorithm -- an optimal strategy for the system within the operating envelope allowed by the permissive strategy. We establish both correctness (with respect to the temporal logic specifications) and optimality (with respect to the a priori unknown performance criterion) of this two-step technique for a fragment of temporal logic specifications. For specifications beyond this fragment, correctness can still be preserved, but the learned strategy may be sub-optimal. We present an algorithm to the overall problem, and demonstrate its use and computational requirements on a set of robot motion planning examples.

 

 

Technical Content © IEEE Robotics & Automation Society


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2019 PaperCept, Inc.
Page generated 2019-07-20  00:38:25 PST  Terms of use