{"total":33,"rows":[{"id":"2104.03113","title":"Scaling Scaling Laws with Board Games","created":"2021-04-07","cited_by_count":63,"area":null},{"id":"2105.07576","title":"Rethinking \"Batch\" in BatchNorm","created":"2021-05-17","cited_by_count":45,"area":null},{"id":"2505.24034","title":"LlamaRL: A Distributed Asynchronous Reinforcement Learning Framework for Efficient Large-scale LLM Training","created":"2025-05-29","cited_by_count":42,"area":null},{"id":"2211.00241","title":"Adversarial Policies Beat Superhuman Go AIs","created":"2022-11-01","cited_by_count":29,"area":null},{"id":"2305.19562","title":"Replicability in Reinforcement Learning","created":"2023-05-31","cited_by_count":21,"area":null},{"id":"2102.08903","title":"Provably Efficient Policy Optimization for Two-Player Zero-Sum Markov Games","created":"2021-02-17","cited_by_count":18,"area":null},{"id":"2211.03769","title":"Are AlphaZero-like Agents Robust to Adversarial Perturbations?","created":"2022-11-07","cited_by_count":14,"area":null},{"id":"2310.11305","title":"MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games","created":"2023-10-17","cited_by_count":14,"area":null},{"id":"2211.14673","title":"Evaluation Beyond Task Performance: Analyzing Concepts in AlphaZero in Hex","created":"2022-11-26","cited_by_count":8,"area":null},{"id":"2112.02563","title":"A Novel Approach to Solving Goal-Achieving Problems for Board Games","created":"2021-12-05","cited_by_count":7,"area":null},{"id":"2102.12375","title":"Transfer of Fully Convolutional Policy-Value Networks Between Games and Game Variants","created":"2021-02-24","cited_by_count":6,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2104.04278","title":"Batch Monte Carlo Tree Search","created":"2021-04-09","cited_by_count":5,"area":null},{"id":"2110.01810","title":"Deep Synoptic Monte Carlo Planning in Reconnaissance Blind Chess","created":"2021-10-05","cited_by_count":4,"area":null},{"id":"2305.04819","title":"Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning","created":"2023-05-08","cited_by_count":4,"area":null},{"id":"2102.03467","title":"Improving Model and Search for Computer Go","created":"2021-02-06","cited_by_count":3,"area":null},{"id":"2201.06401","title":"Spatial State-Action Features for General Games","created":"2022-01-17","cited_by_count":3,"area":null},{"id":"2204.07531","title":"Understanding Game-Playing Agents with Natural Language Annotations","created":"2022-04-15","cited_by_count":3,"area":null},{"id":"2205.12787","title":"Impartial Games: A Challenge for Reinforcement Learning","created":"2022-05-25","cited_by_count":3,"area":null},{"id":"2207.05991","title":"Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environments","created":"2022-07-13","cited_by_count":2,"area":null},{"id":"2412.12024","title":"Learning to Navigate in Mazes with Novel Layouts using Abstract Top-down Maps","created":"2024-12-16","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":"2210.00828","title":"Mastering Spatial Graph Prediction of Road Networks","created":"2022-10-03","cited_by_count":1,"area":null},{"id":"2306.15903","title":"Diversity is Strength: Mastering Football Full Game with Interactive Reinforcement Learning of Multiple AIs","created":"2023-06-28","cited_by_count":1,"area":null},{"id":"2502.17109","title":"Strength Estimation and Human-Like Strength Adjustment in Games","created":"2025-02-24","cited_by_count":1,"area":null},{"id":"2103.17228","title":"OLIVAW: Mastering Othello without Human Knowledge, nor a Fortune","created":"2021-03-31","cited_by_count":0,"area":null},{"id":"2208.12643","title":"The cost of passing -- using deep learning AIs to expand our understanding of the ancient game of Go","created":"2022-08-24","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":"2303.13553","title":"CH-Go: Online Go System Based on Chunk Data Storage","created":"2023-03-22","cited_by_count":0,"area":null},{"id":"2410.05347","title":"Bridging Local and Global Knowledge via Transformer in Board Games","created":"2024-10-07","cited_by_count":0,"area":null},{"id":"2512.21365","title":"A Study of Solving Life-and-Death Problems in Go Using Relevance-Zone Based Solvers","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2606.05967","title":"Fast and Robust Convergence Rate for TD(0) with Linear Function Approximation, Universal Learning Steps and I.I.D. Samples","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2607.26946","title":"Belief-Guided Decision Making with Uncertainty Gating in the Game of Go","created":"2026-07-29","cited_by_count":0,"area":null}],"next_cursor":null}