paper-with-me

Papers

Maia-2: A Unified Model for Human-AI Alignment in Chess

2024-09-30 · Zhenwei Tang, Difan Jiao, Reid McIlroy-Young, Jon Kleinberg, Siddhartha Sen, Ashton Anderson

There are an increasing number of domains in which artificial intelligence (AI) systems both surpass human ability and accurately model human behavior. This introduces the possibility of algorithmically-informed teaching in these domains through more relatable AI partners and deeper insights into human decision-making. Critical to achieving this goal, however, is coherently modeling human behavior at various skill levels. Chess is an ideal model system for conducting research into this kind of human-AI alignment, with its rich history as a pivotal testbed for AI research, mature superhuman AI systems like AlphaZero, and precise measurements of skill via chess rating systems. Previous work in modeling human decision-making in chess uses completely independent models to capture human style at different skill levels, meaning they lack coherence in their ability to adapt to the full spectrum of human improvement and are ultimately limited in their effectiveness as AI partners and teaching tools. In this work, we propose a unified modeling approach for human-AI alignment in chess that coherently captures human style across different skill levels and directly captures how people improve. Recognizing the complex, non-linear nature of human learning, we introduce a skill-aware attention mechanism to dynamically integrate players' strengths with encoded chess positions, enabling our model to be sensitive to evolving player skill. Our experimental results demonstrate that this unified framework significantly enhances the alignment between AI and human players across a diverse range of expertise levels, paving the way for deeper insights into human decision-making and AI-guided teaching tools.

📄 PDF Abstract BibTeX arXiv:2409.20553

Code (2)

csslab/maia2 공식 구현 pytorch
CSSLab/maia-chess pytorch

Tasks

Decision Making

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음
AlphaZero AlphaZero is a reinforcement learning agent for playing board games such as Go, chess, and shogi.

Similar Papers 제목 키워드 기반

Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess

2025-07-29 · Zhenwei Tang, Difan Jiao, Eric Xue, Reid McIlroy-Young 외 arxiv

As humans seek to collaborate with, learn from, and better understand artificial intelligence systems, developing AIs that can accurately emulate individual decision-making becomes increasingly important. Chess, a long-s…

ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess

2026-06-03 · Thomas Johnson arxiv

We present ChessMimic, a system of three small encoder-only transformers - for move, thinking-time, and outcome prediction - conditioned on the position, recent move history, player rating, and clock state. We fit a sepa…

UniMaia: Steering Chess Policies with Language for Human-like Play

2026-05-26 · Sherman Siu, Lesley Istead arxiv

Recent advances in large language models have enabled natural language to serve as a flexible interface for controlling complex systems, but often at the cost of large-scale multimodal training or weakened domain-specifi…

Toward Modeling Player-Specific Chess Behaviors

2026-05-12 · Loris Sogliuzzo, Aloïs Rautureau, Eric Piette arxiv

While artificial intelligence has achieved superhuman performance in chess, developing models that accurately emulate the individualized decision-making styles of human players remains a significant challenge. Existing h…

Chessformer: A Unified Architecture for Chess Modeling

2026-05-18 · Daniel Monroe, George Eilender, Philip Chalmers, Zhenwei Tang 외 arxiv

Chess has long served as a canonical testbed for artificial intelligence, but modeling approaches for its central tasks have diverged. Maximizing playing strength, predicting human play, and enabling interpretability are…