{"total":79,"rows":[{"id":"2111.09259","title":"Acquisition of Chess Knowledge in AlphaZero","created":"2021-11-17","cited_by_count":123,"area":null},{"id":"2106.04537","title":"Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks","created":"2021-06-08","cited_by_count":117,"area":null},{"id":"2306.09200","title":"ChessGPT: Bridging Policy Learning and Language Modeling","created":"2023-06-15","cited_by_count":75,"area":null},{"id":"2112.07544","title":"Modeling Strong and Human-Like Gameplay with KL-Regularized Search","created":"2021-12-14","cited_by_count":50,"area":"offlinerl"},{"id":"2202.01288","title":"Imitation Learning by Estimating Expertise of Demonstrators","created":"2022-02-02","cited_by_count":50,"area":"offlinerl"},{"id":"2402.04494","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","created":"2024-02-07","cited_by_count":49,"area":null},{"id":"2107.08828","title":"Reinforcement Learning for Education: Opportunities and Challenges","created":"2021-07-15","cited_by_count":25,"area":null},{"id":"2409.20553","title":"Maia-2: A Unified Model for Human-AI Alignment in Chess","created":"2024-09-30","cited_by_count":25,"area":null},{"id":"2406.11741","title":"Transcendence: Generative Models Can Outperform The Experts That Train Them","created":"2024-06-17","cited_by_count":20,"area":null},{"id":"2208.01366","title":"Detecting Individual Decision-Making Style: Exploring Behavioral Stylometry in Chess","created":"2022-08-02","cited_by_count":18,"area":null},{"id":"2109.11328","title":"Reinforcement Learning Under Algorithmic Triage","created":"2021-09-23","cited_by_count":15,"area":null},{"id":"2108.08454","title":"Improving Human Sequential Decision-Making with Reinforcement Learning","created":"2021-08-19","cited_by_count":12,"area":null},{"id":"2207.09394","title":"Mimetic Models: Ethical Implications of AI that Acts Like You","created":"2022-07-19","cited_by_count":11,"area":null},{"id":"2410.03893","title":"Human-aligned Chess with a Bit of Search","created":"2024-10-04","cited_by_count":11,"area":null},{"id":"2110.11737","title":"Measuring the Non-Transitivity in Chess","created":"2021-10-22","cited_by_count":10,"area":null},{"id":"2405.05066","title":"Designing Skill-Compatible AI: Methodologies and Frameworks in Chess","created":"2024-05-08","cited_by_count":10,"area":null},{"id":"2205.01265","title":"From {Solution Synthesis} to {Student Attempt Synthesis} for Block-Based Visual Programming Tasks","created":"2022-05-03","cited_by_count":8,"area":null},{"id":"2211.01602","title":"Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration","created":"2022-11-03","cited_by_count":8,"area":null},{"id":"2212.04401","title":"A Rubric for Human-like Agents and NeuroAI","created":"2022-12-08","cited_by_count":8,"area":null},{"id":"2510.23948","title":"ChessQA: Evaluating Large Language Models for Chess Understanding","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2507.21488","title":"Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess","created":"2025-07-29","cited_by_count":7,"area":null},{"id":"2605.19091","title":"Chessformer: A Unified Architecture for Chess Modeling","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2205.07333","title":"Trucks Don't Mean Trump: Diagnosing Human Error in Image Analysis","created":"2022-05-15","cited_by_count":4,"area":null},{"id":"2401.16852","title":"Checkmating One, by Using Many: Combining Mixture of Experts with MCTS to Improve in Chess","created":"2024-01-30","cited_by_count":4,"area":"moe"},{"id":"2404.18978","title":"Towards Generalizable Agents in Text-Based Educational Environments: A Study of Integrating RL with LLMs","created":"2024-04-29","cited_by_count":4,"area":"agents"},{"id":"2405.04118","title":"Policy Learning with a Language Bottleneck","created":"2024-05-07","cited_by_count":4,"area":null},{"id":"2407.13067","title":"Large Language Model Agents for Improving Engagement with Behavior Change Interventions: Application to Digital Mindfulness","created":"2024-07-03","cited_by_count":4,"area":"agents"},{"id":"2409.11506","title":"Chess Rating Estimation from Moves and Clock Times Using a CNN-LSTM","created":"2024-09-17","cited_by_count":4,"area":null},{"id":"2410.12621","title":"Weak-to-Strong Generalization beyond Accuracy: a Pilot Study in Safety, Toxicity, and Legal Reasoning","created":"2024-10-16","cited_by_count":4,"area":"lr"},{"id":"2506.04892","title":"Learning to Plan via Supervised Contrastive Learning and Strategic Interpolation: A Chess Case Study","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2309.09702","title":"Information based explanation methods for deep learning agents -- with applications on large open-source chess models","created":"2023-09-18","cited_by_count":3,"area":null},{"id":"2312.04030","title":"Modeling Boundedly Rational Agents with Latent Inference Budgets","created":"2023-12-07","cited_by_count":3,"area":null},{"id":"2503.16468","title":"Towards properly implementing Theory of Mind in AI systems: An account of four misconceptions","created":"2025-02-28","cited_by_count":3,"area":null},{"id":"2509.24239","title":"ChessArena: A Chess Testbed for Evaluating Strategic Reasoning Capabilities of Large Language Models","created":"2025-09-29","cited_by_count":3,"area":"lr"},{"id":"2609.16679","title":"AI for Games in the Foundation Model Era","created":"2026-09-15","cited_by_count":3,"area":"wm"},{"id":"2406.11895","title":"Predicting User Perception of Move Brilliance in Chess","created":"2024-06-14","cited_by_count":2,"area":null},{"id":"2501.19301","title":"Beyond checkmate: exploring the creative chokepoints in AI text","created":"2025-01-31","cited_by_count":2,"area":null},{"id":"2502.14998","title":"Generative Modeling of Individual Behavior at Scale","created":"2025-02-20","cited_by_count":2,"area":null},{"id":"2603.07705","title":"Deep Incentive Design with Differentiable Equilibrium Blocks","created":"2026-03-08","cited_by_count":2,"area":null},{"id":"2205.00254","title":"PGD: A Large-scale Professional Go Dataset for Data-driven Analytics","created":"2022-04-30","cited_by_count":1,"area":null},{"id":"2507.05868","title":"CogniPlay: a work-in-progress Human-like model for General Game Playing","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2602.04447","title":"Mixture of Masters: Sparse Chess Language Models with Player Routing","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.05352","title":"Ailed: A Psyche-Driven Chess Engine with Dynamic Emotional Modulation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2605.11893","title":"Toward Modeling Player-Specific Chess Behaviors","created":"2026-05-12","cited_by_count":1,"area":null},{"id":"2606.25176","title":"Matilda: Engine-Agnostic Search with Human Policy Guidance","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2609.00474","title":"Exploring Collaboration between a language and a non-language agent","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.01591","title":"StudentSim: Training LLM-based Student Simulators","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2112.08093","title":"Towards Controllable Agent in MOBA Games with Generative Modeling","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2207.09619","title":"Learning Latent Traits for Simulated Cooperative Driving Tasks","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2210.08289","title":"AI-powered mechanisms as judges: Breaking ties in chess","created":"2022-10-15","cited_by_count":0,"area":null},{"id":"2211.01559","title":"The ProfessionAl Go annotation datasEt (PAGE)","created":"2022-11-03","cited_by_count":0,"area":null},{"id":"2407.04678","title":"XQSV: A Structurally Variable Network to Imitate Human Play in Xiangqi","created":"2024-07-05","cited_by_count":0,"area":null},{"id":"2504.05425","title":"A Behavior-Based Knowledge Representation Improves Prediction of Players' Moves in Chess by 25%","created":"2025-04-07","cited_by_count":0,"area":null},{"id":"2505.00279","title":"Policies of Multiple Skill Levels for Better Strength Estimation in Games","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2508.13213","title":"AI sustains higher strategic tension than humans in chess","created":"2025-08-16","cited_by_count":0,"area":null},{"id":"2509.15263","title":"Subject Matter Expertise vs Professional Management in Collective Sequential Decision Making","created":"2025-09-18","cited_by_count":0,"area":null},{"id":"2509.20666","title":"Understanding Role Switching in Human-AI Collaboration through Multimodal Behavioral Signals","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2509.25475","title":"TDHook: A Lightweight Framework for Interpretability","created":"2025-09-29","cited_by_count":0,"area":"deeprl"},{"id":"2601.05386","title":"How Much Can a Few Engine Moves Help? Quantifying Limited Cheating in Chess","created":"2026-01-08","cited_by_count":0,"area":null},{"id":"2601.21771","title":"Abstract Concept Modelling in Conceptual Spaces: A Study on Chess Strategies","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.23318","title":"Generalized Rapid Action Value Estimation in Memory-Constrained Environments","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.29761","title":"Tracking vs. Deciding: The Dual-Capability Bottleneck in Searchless Chess Transformers","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.03565","title":"Personality Requires Struggle: Three Regimes of the Baldwin Effect in Neuroevolved Chess Agents","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.14465","title":"Improving Human Performance with Value-Aware Interventions: A Case Study in Chess","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2606.04473","title":"ChessMimic: Per-Rating Transformer Models for Human Move, Clock, and Outcome Prediction in Online Blitz Chess","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.28166","title":"Tandem Reinforcement Learning with Verifiable Rewards","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.00190","title":"Play Like Champions: Counterfactual Feedback Generation in Latent Space","created":"2026-06-30","cited_by_count":0,"area":"deeprl"},{"id":"2607.11486","title":"Communicating Chess Strategies in Natural Language","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.11501","title":"Comparative Analysis of GAT and BERT for Human-Like Playtesting","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.25655","title":"Engine-Equal, Human-Unequal: A Reproducible Outcome Skew in Engine-Assessed Equal Chess Positions","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.27574","title":"Policy Gradient Steering: Interventions from Behavioral Objectives","created":"2026-07-30","cited_by_count":0,"area":"mechinterp"},{"id":"2608.05206","title":"Otter: A Time-Aware, History-Conditioned Human Chess AI","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.21398","title":"Runtime Action Interference for AI Control of AlphaStar in StarCraft II","created":"2026-08-05","cited_by_count":0,"area":"deeprl"},{"id":"2608.27757","title":"Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.14422","title":"Safety Signals to Verify NetOps Agents with Action-Level Granularity","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.18286","title":"What Counts as Strategic Reasoning? A Systematic Mapping of Chess Research on Humans, Engines, and Language Models","created":"2026-09-16","cited_by_count":0,"area":"lr"},{"id":"2609.23917","title":"Increasing Skill Level Recruits Deeper Attention Layers in a Frozen Chess Transformer","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.35835","title":"Amadeus: When Models of People Meet","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.03695","title":"Language Models that Play Chess and Explain Their Moves","created":"2026-10-02","cited_by_count":0,"area":null}],"next_cursor":null}