Tank War Using Online Reinforcement Learning

Real-Time Strategy(RTS) games provide a challenging platform to implement online reinforcement learning(RL) techniques in a real application. Computer as one player monitors opponents'(human or other computers) strategies and then updates its own policy using RL methods. In this paper, we propo...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the 2009 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology - Volume 02 Vol. 2; pp. 497 - 500
Main Authors: Andersen, Kresten Toftgaard, Zeng, Yifeng, Christensen, Dennis Dahl, Tran, Dung
Format: Conference Proceeding
Language:English
Published: Washington, DC, USA IEEE Computer Society 15.09.2009
IEEE
Series:ACM Conferences
Subjects:
Application software
Cities and towns
Computer applications
Computer science
Computing methodologies > Artificial intelligence > Control methods
Computing methodologies > Artificial intelligence > Search methodologies
Computing methodologies > Machine learning
Computing methodologies > Modeling and simulation > Model development and analysis > Modeling methodologies
Conferences
Humans
Intelligent agent
Learning
Real-Time Strategy Game
Reinforcement Learning
State-space methods
Testing
Theory of computation > Design and analysis of algorithms > Algorithm design techniques > Dynamic programming
Theory of computation > Design and analysis of algorithms > Online algorithms > Online learning algorithms
Theory of computation > Models of computation > Interactive computation
Theory of computation > Theory and algorithms for application domains > Machine learning theory > Online learning theory
Real-Time Strategy Game
Reinforcement Learning
ISBN:0769538010, 9780769538013
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Real-Time Strategy(RTS) games provide a challenging platform to implement online reinforcement learning(RL) techniques in a real application. Computer as one player monitors opponents'(human or other computers) strategies and then updates its own policy using RL methods. In this paper, we propose a multi-layer framework for implementing the online RL in a RTS game. The framework significantly reduces the RL computational complexity by decomposing the state space in a hierarchical manner. We implement the RTS game - Tank General, and perform a thorough test on the proposed framework. The results show the effectiveness of our proposed framework and shed light on relevant issues on using the RL in RTS games.
ISBN:0769538010
9780769538013
DOI:10.1109/WI-IAT.2009.201