# Learning Models of Individual Behavior in Chess

arXiv: https://arxiv.org/abs/2008.10086 · HTML: https://mlsanity.com/paper/2008.10086/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Aug 2020.

## Built on by (most cited first, 22 of 22)

- [Amortized Planning with Large-Scale Transformers: A Case Study on Chess](https://mlsanity.com/paper/2402.04494/) (2024)
- [Maia-2: A Unified Model for Human-AI Alignment in Chess](https://mlsanity.com/paper/2409.20553/) (2024)
- [Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess](https://mlsanity.com/paper/2507.21488/) (2025)
- [Chessformer: A Unified Architecture for Chess Modeling](https://mlsanity.com/paper/2605.19091/) (2026)
- [Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess](https://mlsanity.com/paper/2401.16852/) (2024)
- [Chess Rating Estimation from Moves and Clock Times Using a CNN-LSTM](https://mlsanity.com/paper/2409.11506/) (2024)
- [Modeling Boundedly Rational Agents with Latent Inference Budgets](https://mlsanity.com/paper/2312.04030/) (2023)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [Generative Modeling of Individual Behavior at Scale](https://mlsanity.com/paper/2502.14998/) (2025)
- [Mixture of Masters: Sparse Chess Language Models with Player Routing](https://mlsanity.com/paper/2602.04447/) (2026)
- [Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation](https://mlsanity.com/paper/2603.05352/) (2026)
- [Matilda: Engine-Agnostic Search with Human Policy Guidance](https://mlsanity.com/paper/2606.25176/) (2026)
- [The ProfessionAl Go annotation datasEt (PAGE)](https://mlsanity.com/paper/2211.01559/) (2022)
- [Play Style Identification Using Low-Level Representations of Play Traces in MicroRTS](https://mlsanity.com/paper/2507.10172/) (2025)
- [How Much Can a Few Engine Moves Help? Quantifying Limited Cheating in Chess](https://mlsanity.com/paper/2601.05386/) (2026)
- [Personality Requires Struggle: Three Regimes of the Baldwin Effect in Neuroevolved Chess Agents](https://mlsanity.com/paper/2604.03565/) (2026)
- [Improving Human Performance with Value-Aware Interventions: A Case Study in Chess](https://mlsanity.com/paper/2604.14465/) (2026)
- [BEACON: A Multimodal Dataset for Learning Behavioral Fingerprints from Gameplay Data](https://mlsanity.com/paper/2605.10867/) (2026)
- [ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess](https://mlsanity.com/paper/2606.04473/) (2026)
- [Towards Learning Representations of Policies in Two-Player Zero-Sum Imperfect-Information Games](https://mlsanity.com/paper/2607.01498/) (2026)
- [Otter: A Time-Aware, History-Conditioned Human Chess AI](https://mlsanity.com/paper/2608.05206/) (2026)
- [Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning](https://mlsanity.com/paper/2608.14851/) (2026)

## Abstract (arXiv)

AI systems that can capture human-like behavior are becoming increasingly useful in situations where humans may want to learn from these systems, collaborate with them, or engage with them as partners for an extended duration. In order to develop human-oriented AI systems, the problem of predicting human actions -- as opposed to predicting optimal actions -- has received considerable attention. Existing work has focused on capturing human behavior in an aggregate sense, which potentially limits the benefit any particular individual could gain from interaction with these systems. We extend this line of work by developing highly accurate predictive models of individual human behavior in chess. Chess is a rich domain for exploring human-AI interaction because it combines a unique set of properties: AI systems achieved superhuman performance many years ago, and yet humans still interact with them closely, both as opponents and as preparation tools, and there is an enormous corpus of recorded data on individual player games. Starting with Maia, an open-source version of AlphaZero trained on a population of human players, we demonstrate that we can significantly improve prediction accuracy of a particular player's moves by applying a series of fine-tuning methods. Furthermore, our personalized models can be used to perform stylometry -- predicting who made a given set of moves -- indicating that they capture human decision-making at an individual level. Our work demonstrates a way to bring AI systems into better alignment with the behavior of individual people, which could lead to large improvements in human-AI interaction.