Safely using predictions in general-sum normal form games

Steven Damer, Maria L Gini

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

3 Scopus citations

Abstract

It is often useful to predict opponent behavior when playing a general- sum two-player normal form game. However best-responding to an inaccurate prediction can lead to a strategy which is vulnerable to exploitation. This paper proposes a novel method, Restricted Stackelberg Response with Safety (RSRS), for an agent to select a strategy to respond to a prediction. The agent uses the confidence it has in the prediction and a safety margin which reflects the level of risk it is willing to tolerate to make a controlled trade-off be-Tween best-responding to the prediction and providing a guarantee of worst-case performance. We describe an algorithm which selects parameter values for RSRS to produce strategies that play well against the prediction, respond to a best-responding opponent, and guard against worst-case outcomes. We report results obtained by the algorithm on multiple general-sum games against different opponents.

Original languageEnglish (US)
Title of host publication16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017
EditorsSanmay Das, Edmund Durfee, Kate Larson, Michael Winikoff
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS)
Pages924-932
Number of pages9
ISBN (Electronic)9781510855076
StatePublished - Jan 1 2017
Event16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017 - Sao Paulo, Brazil
Duration: May 8 2017May 12 2017

Publication series

NameProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS
Volume2
ISSN (Print)1548-8403
ISSN (Electronic)1558-2914

Other

Other16th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2017
Country/TerritoryBrazil
CitySao Paulo
Period5/8/175/12/17

Keywords

  • Game theory
  • General-sum normal form games
  • Prediction errors
  • Risk management

Cite this