Game Redesign in No-Regret Game Playing

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 players to take a specific target action profile frequently; (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. Simulations on four classic games confirm the ef- fectiveness of our proposed redesign algorithms.

Cite

Text

Ma et al. "Game Redesign in No-Regret Game Playing." International Joint Conference on Artificial Intelligence, 2022. doi:10.24963/IJCAI.2022/461

Markdown

[Ma et al. "Game Redesign in No-Regret Game Playing." International Joint Conference on Artificial Intelligence, 2022.](https://mlanthology.org/ijcai/2022/ma2022ijcai-game/) doi:10.24963/IJCAI.2022/461

BibTeX

@inproceedings{ma2022ijcai-game,
  title     = {{Game Redesign in No-Regret Game Playing}},
  author    = {Ma, Yuzhe and Wu, Young and Zhu, Xiaojin},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2022},
  pages     = {3321-3327},
  doi       = {10.24963/IJCAI.2022/461},
  url       = {https://mlanthology.org/ijcai/2022/ma2022ijcai-game/}
}