Empirical Analysis of Fictitious Play for Nash Equilibrium Computation in Multiplayer Games

 0 Người đánh giá. Xếp hạng trung bình 0

Tác giả: Sam Ganzfried

Ngôn ngữ: eng

Ký hiệu phân loại: 519.3 Game theory

Thông tin xuất bản: 2020

Mô tả vật lý:

Bộ sưu tập: Metadata

ID: 163889

Comment: Subsumes 2020 article "Fictitious Play Outperforms Counterfactual Regret Minimization" and 2022 article "Random Initialization Solves Shapley's Fictitious Play Counterexample."While fictitious play is guaranteed to converge to Nash equilibrium in certain game classes, such as two-player zero-sum games, it is not guaranteed to converge in non-zero-sum and multiplayer games. We show that fictitious play in fact leads to improved Nash equilibrium approximation over a variety of game classes and sizes than (counterfactual) regret minimization, which has recently produced superhuman play for multiplayer poker. We also show that when fictitious play is run several times using random initializations it is able to solve several known challenge problems in which the standard version is known to not converge, including Shapley's classic counterexample. These provide some of the first positive results for fictitious play in these settings, despite the fact that worst-case theoretical results are negative.
Tạo bộ sưu tập với mã QR

THƯ VIỆN - TRƯỜNG ĐẠI HỌC CÔNG NGHỆ TP.HCM

ĐT: (028) 36225755 | Email: tt.thuvien@hutech.edu.vn

Copyright @2024 THƯ VIỆN HUTECH