Opponent modeling under partial observability in starcraft with deep convolutional encoder-decoders

Hyungu Kahng, Seoung Bum Kim

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

Abstract

StarCraft, one of the most popular real-time strategy games, is a compelling environment for artificial intelligence research involving various tasks of both micro-level unit control and macro-level strategic decision making. In this study, we address an eminent problem of concern in macro-level decision making known as the “fog-of-war”, which rises from the partial observable nature of the game. Recovering information hidden under the fog can help capture advantageous high-level game dynamics, such as build orders, tactics and strategies of the opponent. Casted as a supervised learning problem, we propose a convolutional encoder-decoder architecture to predict potential counts and locations of the opponent’s units based on only partially visible and noisy state information. We visualize the model predictions on simplified grids to primarily evaluate the performance of our proposed method. Furthermore, we train an additional convolutional neural network classifier on the encoder-decoder outputs to predict the final winner of the game, as a means of demonstrating both effectiveness and applicability.

Original languageEnglish
Title of host publicationIntelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 1
EditorsYaxin Bi, Rahul Bhatia, Supriya Kapoor
PublisherSpringer Verlag
Pages751-759
Number of pages9
ISBN (Print)9783030295158
DOIs
Publication statusPublished - 2020 Jan 1
EventIntelligent Systems Conference, IntelliSys 2019 - London, United Kingdom
Duration: 2019 Sep 52019 Sep 6

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1037
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceIntelligent Systems Conference, IntelliSys 2019
CountryUnited Kingdom
CityLondon
Period19/9/519/9/6

Keywords

  • Convolutional neural networks
  • Fog-of-war
  • StarCraft

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Opponent modeling under partial observability in starcraft with deep convolutional encoder-decoders'. Together they form a unique fingerprint.

  • Cite this

    Kahng, H., & Kim, S. B. (2020). Opponent modeling under partial observability in starcraft with deep convolutional encoder-decoders. In Y. Bi, R. Bhatia, & S. Kapoor (Eds.), Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference IntelliSys Volume 1 (pp. 751-759). (Advances in Intelligent Systems and Computing; Vol. 1037). Springer Verlag. https://doi.org/10.1007/978-3-030-29516-5_56