English

Game Redesign in No-regret Game Playing

Computer Science and Game Theory 2021-10-25 v1 Machine Learning

Abstract

We study the game redesign problem in which an external designer has the ability to change the payoff function in each round, but incurs a design cost for deviating from the original game. The players apply no-regret learning algorithms to repeatedly play the changed games with limited feedback. The goals of the designer are to (i) incentivize all players to take a specific target action profile frequently; and (ii) incur small cumulative design cost. We present game redesign algorithms with the guarantee that the target action profile is played in T-o(T) rounds while incurring only o(T) cumulative design cost. Game redesign describes both positive and negative applications: a benevolent designer who incentivizes players to take a target action profile with better social welfare compared to the solution of the original game, or a malicious attacker whose target action profile benefits themselves but not the players. Simulations on four classic games confirm the effectiveness of our proposed redesign algorithms.

Keywords

Cite

@article{arxiv.2110.11763,
  title  = {Game Redesign in No-regret Game Playing},
  author = {Yuzhe Ma and Young Wu and Xiaojin Zhu},
  journal= {arXiv preprint arXiv:2110.11763},
  year   = {2021}
}
R2 v1 2026-06-24T07:06:18.554Z