Ad Hoc Teamwork With Behavior Switching Agents release_krr7vjqo2nfcdnjdkuptct3baq

by Manish Ravula, Shani Alkoby, Peter Stone

Published in International Joint Conference on Artificial Intelligence by International Joint Conferences on Artificial Intelligence Organization.

2019   p550-556

Abstract

As autonomous AI agents proliferate in the real world, they will increasingly need to cooperate with each other to achieve complex goals without always being able to coordinate in advance. This kind of cooperation, in which agents have to learn to cooperate on the fly, is called ad hoc teamwork. Many previous works investigating this setting assumed that teammates behave according to one of many predefined types that is fixed throughout the task. This assumption of stationarity in behaviors, is a strong assumption which cannot be guaranteed in many real-world settings. In this work, we relax this assumption and investigate settings in which teammates can change their types during the course of the task. This adds complexity to the planning problem as now an agent needs to recognize that a change has occurred in addition to figuring out what is the new type of the teammate it is interacting with. In this paper, we present a novel Convolutional-Neural-Network-based Change point Detection (CPD) algorithm for ad hoc teamwork. When evaluating our algorithm on the modified predator prey domain, we find that it outperforms existing Bayesian CPD algorithms.
In application/xml+jats format

Archived Files and Locations

application/pdf  358.8 kB
file_fnxcilsqafgvlkegt5b5igiiae
www.cs.utexas.edu (web)
web.archive.org (webarchive)
application/pdf  263.4 kB
file_d33defzml5d5ff7zm7tvnmjtoe
www.ijcai.org (web)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  paper-conference
Stage   published
Year   2019
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 891f29ab-0b59-473e-b851-6b333163cae6
API URL: JSON