Publications

• Sorted by Date • Classified by Publication Type • Classified by Research Category •

Environment Shift Games: Are Multiple Agents the Solution, and not the Problem, to Non-Stationarity?

Alexander Mey and Frans A. Oliehoek. Environment Shift Games: Are Multiple Agents the Solution, and not the Problem, to Non-Stationarity?. In Proceedings of the Twentieth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 23–27, May 2021. Blue Sky Track. Special Mention.

Download

pdf [747.7kB]  

Abstract

Machine learning and artificial intelligence models that interact with and in an environment will unavoidably have impact on this environment and change it. This is often a problem as many methods do not anticipate such a change in the environment and thus may start acting sub-optimally.Although efforts are made to deal with this problem, we believe that a lot ofpotential is unused. Driven by the recent success of predictive machinelearning, we believe that in many scenarios one can predict when and how achange in the environment will occur. In this paper we introduce a blueprintthat intimately connects this idea to the multiagent setting, showing that themultiagent community has a pivotal role to play in addressing the challengingproblem of changing environments.

BibTeX Entry

@inproceedings{Mey21AAMAS,
    author= { Alexander Mey and
            Frans A. Oliehoek},
    title =     {Environment Shift Games: Are Multiple Agents the Solution, and not the Problem, to Non-Stationarity?},
    booktitle = AAMAS21,
    year =      2021,
    month =     may,
    pages =     {23--27},
    keywords =   {refereed},
    note =      {Blue Sky Track. \textbf{Special Mention.}},
    abstract = {
Machine learning and artificial intelligence models that interact with and in
    an environment will unavoidably have impact on this environment and change
    it. This is often a problem as many methods do not anticipate such a change
    in the environment and thus may start acting sub-optimally.
Although efforts are made to deal with this problem, we believe that a lot of
potential is unused. Driven by the recent success of predictive machine
learning, we believe that in many scenarios one can predict when and how a
change in the environment will occur. In this paper we introduce a blueprint
that intimately connects this idea to the multiagent setting, showing that the
multiagent community has a pivotal role to play in addressing the challenging
problem of changing environments.  }
}

Generated by bib2html.pl (written by Patrick Riley) on Mon Apr 08, 2024 20:28:07 UTC