Can I Do That? Discovering Domain Axioms Using Declarative Programming and Relational Reinforcement Learning

Mohan Sridharan*, Prashanth Devarakonda, Rashmica Gupta

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

Robots deployed to assist humans in complex, dynamic domains need the ability to represent, reason with, and learn from, different descriptions of incomplete domain knowledge and uncertainty. This paper presents an architecture that integrates declarative programming and relational reinforcement learning to support cumulative and interactive discovery of previously unknown axioms governing domain dynamics. Specifically, Answer Set Prolog (ASP), a declarative programming paradigm, is used to represent and reason with incomplete commonsense domain knowledge. For any given goal, unexplained failure of plans created by inference in the ASP program is taken to indicate the existenceof unknown domain axioms. The task of learning these axioms is formulatedas a Reinforcement Learning problem, and decision-tree regression with a relational representation is used to generalize from specific axioms identified over time. The new axioms are added to the ASP-based representationfor subsequent inference. We demonstrate and evaluate the capabilities of our architecture in two simulated domains: Blocks World and Simple Mario.
Original languageEnglish
Title of host publicationAutonomous Agents and Multiagent Systems
EditorsNardine Osman, Carles Sierra
PublisherSpringer
Pages34-49
Number of pages16
ISBN (Print)9783319468396
DOIs
Publication statusPublished - 24 Sept 2016
EventAAMAS 2016 : International Conference on Autonomous Agents and Multiagent Systems - , Singapore
Duration: 9 May 201613 May 2016
https://sis.smu.edu.sg/aamas2016?itemid=671

Publication series

NameLecture Notes in Computer Science
PublisherSpringer

Conference

ConferenceAAMAS 2016 : International Conference on Autonomous Agents and Multiagent Systems
Abbreviated titleAAMAS 2016
Country/TerritorySingapore
Period9/05/1613/05/16
Internet address

Fingerprint

Dive into the research topics of 'Can I Do That? Discovering Domain Axioms Using Declarative Programming and Relational Reinforcement Learning'. Together they form a unique fingerprint.

Cite this