Fast learning against adaptive adversarial opponents

Mohamed Elidrisi, Nicholas Johnson, Maria Gini

Research output: Contribution to conferencePaperpeer-review

7 Scopus citations

Abstract

The ability to learn and adapt when playing against an adaptive opponent requires the ability to predict the opponent's behavior. Capturing any changes in the opponent's behavior during a sequence of plays is critical to achieve positive outcomes in such an environment. We identify two new requirements that we suggest are essential for agents that learn in adaptive environments. These requirements are dictated by the fact that repeated interactions in practice have to be limited and that the opponent can rapidly change strategy through the sequence of interactions. We believe that building intelligent agents that can survive in environments with such requirements will lead to wider deployment of learning agents. We propose a novel algorithm that is able to learn and adapt rapidly to an opponent even when the number of interactions is limited and the opponent is adapting quickly by changing its strategy. The context we use for the experimental work is two player normal form games. We compare the performance of an agent using our algorithm against agents using existing multiagent learning algorithms.

Original languageEnglish (US)
Pages145-152
Number of pages8
StatePublished - Dec 1 2012
Event2012 Workshop on Adaptive and Learning Agents, ALA 2012 - Held in Conjunction with the 11th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2012 - Valencia, Spain
Duration: Jun 4 2012Jun 5 2012

Other

Other2012 Workshop on Adaptive and Learning Agents, ALA 2012 - Held in Conjunction with the 11th International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2012
Country/TerritorySpain
CityValencia
Period6/4/126/5/12

Fingerprint

Dive into the research topics of 'Fast learning against adaptive adversarial opponents'. Together they form a unique fingerprint.

Cite this