Simulation of multi-robot reinforcement learning for box-pushing problem

被引：17

作者：

Kovac, K ^{[1
]}

Zivkovic, I ^{[1
]}

Basic, BD ^{[1
]}

机构：

[1] Univ Zagreb, Fac Elect & Comp Engn, Dept Elect Microelect Comp & Intelligent Syst, Zagreb 41000, Croatia

来源：

MELECON 2004: PROCEEDINGS OF THE 12TH IEEE MEDITERRANEAN ELECTROTECHNICAL CONFERENCE, VOLS 1-3 | 2004年

关键词：

D O I：

10.1109/MELCON.2004.1347002

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

The box-pushing problem represents a challenging domain for the study of object manipulation in a multi-robot environment. Our box-pushing problem is based on the pusher-watcher approach, involving two pushers robots that learn the best strategy for cooperatively moving an oversized elongated box to a specified goal and one watcher robot acting as the environment. This paper presents a solution to the box-pushing problem based on reinforcement learning in a multi-agent system. Within the framework of the paper, a simulator has been developed to carry out practical tests.

引用

页码：603 / 606

页数：4

共 9 条

[1]

[Anonymous], MULTI AGENT SYSTEMS

[2]

Gerkey BP, 2002, 2002 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION, VOLS I-IV, PROCEEDINGS, P464, DOI 10.1109/ROBOT.2002.1013403

[3] AUTOMATIC PROGRAMMING OF BEHAVIOR-BASED ROBOTS USING REINFORCEMENT LEARNING [J].

MAHADEVAN, S ;

CONNELL, J .

ARTIFICIAL INTELLIGENCE, 1992, 55 (2-3) :311-365

[4]

MATARIC MJ, 1995, IROS '95 - 1995 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS: HUMAN ROBOT INTERACTION AND COOPERATIVE ROBOTS, PROCEEDINGS, VOL 3, P556, DOI 10.1109/IROS.1995.525940

[5] Reinforcement learning in the multi-robot domain [J].

Mataric, MJ .

AUTONOMOUS ROBOTS, 1997, 4 (01) :73-83

[6] Using communication to reduce locality in distributed multiagent learning [J].

Mataric, MJ .

JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 1998, 10 (03) :357-369

[7]

SIMSARIAN KT, 1995, P 3 EUR WORKSH LEARN

[8]

Stone P., 2000, INTEL ROB AUTON AGEN

[9]

Sutton R. S., 1998, Reinforcement Learning: An Introduction, V22447

← 1 →