Adaptive high-level strategy learning in starcraft

Jieverson Maissiat, Felipe Meneguzzi

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

Abstract

Reinforcement learning (RL) is a technique to compute an optimal policy in stochastic settings whereby, actions from an initial policy are simulated (or directly executed) and the value of a state is updated based on the immediate rewards obtained as the policy is executed. Existing efforts model opponents in
competitive games as elements of a stochastic environment and use RL to learn policies against such opponents. In this setting, the rate of change for state values monotonically decreases over time, as learning converges. Although this modeling assumes that the opponent strategy is static over time, such an assumption is too strong when human opponents are possible. Consequently, in
this paper, we develop a meta-level RL mechanism that detects when an opponent changes strategy and allows the state-values to “deconverge” in order to learn how to play against a different strategy. We validate this approach empirically for high-level strategy selection in the Starcraft: Brood War game.
Original languageEnglish
Title of host publicationProceedings of the SBGames conference on Computing
Pages17-24
Number of pages8
Publication statusPublished - 2013
Externally publishedYes

Bibliographical note

XII SBGames – São Paulo – SP – Brazil, October 16th - 18th, 2013

Fingerprint

Dive into the research topics of 'Adaptive high-level strategy learning in starcraft'. Together they form a unique fingerprint.

Cite this