A Generalized Extensive-Form Fictitious Play Algorithm

Tim P. Schulze
10/14/2023
cs.GTcs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

We introduce a simple extensive-form algorithm for finding equilibria of two-player, zero-sum games. The algorithm is realization equivalent to a generalized form of Fictitious Play. We compare its performance to that of a similar extensive-form fictitious play algorithm and a counter-factual regret minimization algorithm. All three algorithms share the same advantages over normal-form fictitious play in terms of reducing storage requirements and computational complexity. The new algorithm is intuitive and straightforward to implement, making it an appealing option for those looking for a quick and easy game solving tool.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

85% match2026

Quadratic Programming Approach for Nash Equilibrium Computation in Multiplayer Imperfect-Information Games

85% match2025

Simulation-Free PSRO: Removing Game Simulation from Policy Space Response Oracles

83% match1 repo22025

The Computational Complexity of Single-Player Imperfect-Recall Games

83% match2023

A Deep Reinforcement Learning Approach for Finding Non-Exploitable Strategies in Two-Player Atari Games

82% match2 repos522022

A Data Driven Structural Decomposition of Dynamic Games via Best Response Maps

82% match2026

Cite this paper

@article{schulze2023generalized,
  title  = {A Generalized Extensive-Form Fictitious Play Algorithm},
  author = {Tim P. Schulze},
  year   = {2023},
  eprint = {2310.09658},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.09658v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.09658.svg)](https://codeofpaper.com/paper/2310.09658)

Discussion