Mastering Strategy Card Game (legends Of Code And Magic) Via End-to-end Policy And Optimistic Smooth Fictitious Play

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyxi2023mastering

Related papers

• Provably Efficient Fictitious Play Policy Optimization For Zero-sum Markov Games With Structured Transitions (2022)0.00
• Learning To Play No-press Diplomacy With Best Response Policy Iteration (2020)0.00
• Anticipatory Fictitious Play (2022)0.00
• Fictitious Cross-play: Learning Global Nash Equilibrium In Mixed Cooperative-competitive Games (2023)3.58
• Deep Reinforcement Learning From Self-play In Imperfect-information Games (2016)0.00
• Improving Fictitious Play Reinforcement Learning With Expanding Models (2019)0.00
• Achieving Correlated Equilibrium By Studying Opponent's Behavior Through Policy-based Deep Reinforcement Learning (2020)0.00
• Mastering Complex Control In MOBA Games With Deep Reinforcement Learning (2019)0.00