21
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      A Courteous Learning Rule for Ad-hoc Anti-coordination

      Preprint
      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          In this paper, we investigate the problem of anti-coordination under rationality constraints in ad-hoc resource allocation settings. Inspired by human behavior, we propose a framework (CA3NONY) that enables fast convergence to efficient and fair allocations based on a simple convention of courtesy. We prove that following such convention induces a strategy which constitutes an approximate subgame-perfect equilibrium of the repeated resource allocation game with discounting. Simulation results highlight the effectiveness of CA3NONY as compared to state-of-the-art bandit algorithms, since it achieves more than two orders of magnitude faster convergence, higher efficiency, fairness, and average payoff for the agents.

          Related collections

          Most cited references11

          • Record: found
          • Abstract: not found
          • Article: not found

          The Nonstochastic Multiarmed Bandit Problem

            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            The Economics of Convention

            H. Young (1996)
              Bookmark
              • Record: found
              • Abstract: not found
              • Article: not found

              Computing correlated equilibria in multi-player games

                Bookmark

                Author and article information

                Journal
                22 January 2018
                Article
                1801.07140
                d11c20d6-63c5-45e9-ae92-246dd1d7d628

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                cs.MA

                Comments

                Comment on this article