Home // ICAS 2012, The Eighth International Conference on Autonomic and Autonomous Systems // View article

Action Learning with Reactive Answer Set Programming: Preliminary Report

Authors:
Michal Certicky

Keywords: ASP, learning, actions, induction

Abstract:
Action learning is a process of automatic induction of knowledge about domain dynamics. The idea to use Answer Set Programming (ASP) for the purposes of action learning has already been published in [2]. However, in reaction to latest introduction of Reactive ASP and implementation of effective tools [6], we propose a slightly different approach, and show how using the Reactive ASP together with more compact knowledge encoding can provide significant advantages. The technique proposed in this paper allows for real-time induction of action models in larger domains, and can be easily modified to deal with sensoric noise and non-determinism. On the other hand, it lacks the ability to learn the conditional effects.

Pages: 107 to 111

Copyright: Copyright (c) IARIA, 2012

Publication date: March 25, 2012

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-61208-187-8

Location: St. Maarten, The Netherlands Antilles

Dates: from March 25, 2012 to March 30, 2012