Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play
Machine Learning
2023-03-08 v1 Artificial Intelligence
Computer Science and Game Theory
Abstract
Deep Reinforcement Learning combined with Fictitious Play shows impressive results on many benchmark games, most of which are, however, single-stage. In contrast, real-world decision making problems may consist of multiple stages, where the observation spaces and the action spaces can be completely different across stages. We study a two-stage strategy card game Legends of Code and Magic and propose an end-to-end policy to address the difficulties that arise in multi-stage game. We also propose an optimistic smooth fictitious play algorithm to find the Nash Equilibrium for the two-player game. Our approach wins double championships of COG2022 competition. Extensive studies verify and show the advancement of our approach.
Keywords
Cite
@article{arxiv.2303.04096,
title = {Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play},
author = {Wei Xi and Yongxin Zhang and Changnan Xiao and Xuefeng Huang and Shihong Deng and Haowei Liang and Jie Chen and Peng Sun},
journal= {arXiv preprint arXiv:2303.04096},
year = {2023}
}