paper-with-me

Papers

AlphaZero in Sparsely Rewarded Games: Limits and Auxiliary Supervision

2026-07-09 · Brent Kong, Tejas Ram, Tony Yue Yu arxiv

AlphaZero has demonstrated that a neural-guided Monte Carlo Tree Search can achieve superhuman performance, but strong play does not necessarily imply perfect play. We study this gap in two oracle-evaluable domains with contrasting structure: Connect Four, a solved partisan game with exact game-theoretic values, and Chomp, an impartial game whose optimal play is governed by Grundy-number structure. Under a unified self-play $+$ MCTS pipeline, we compare vanilla AlphaZero, a multi-frame variant (limited to Chomp), and an AlphaZero Auxiliary Loss (AZAL) that adds oracle-derived policy supervision. We find that vanilla AlphaZero achieves strong play across both domains but cannot preserve the exact trajectories required for optimal play: in Connect Four, it fails to maintain the optimal line of play, while in Chomp, it fails to consistently restore the $g=0$ invariant. On rectangular Chomp boards, multi-frame inputs alone do not remove this gap. Nevertheless, AZAL substantially improves oracle consistency across multi-seeded full-game traces and sampled-state evaluations. On Chomp, AZAL reaches perfect full-game oracle consistency on 10x11 and high but not complete consistency on 9x10; on Connect Four, AZAL improves oracle-match rate and delays the first oracle mistake, but does not reach perfect play.

📄 PDF Abstract BibTeX arXiv:2607.08984

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multiplayer AlphaZero

2019-10-29 · Nick Petosa, Tucker Balch

The AlphaZero algorithm has achieved superhuman performance in two-player, deterministic, zero-sum games where perfect information of the game state is available. This success has been demonstrated in Chess, Shogi, and G…

Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN

2021-07-18 · Shai Ben-Assayag, Ran El-Yaniv

Playing board games is considered a major challenge for both humans and AI researchers. Because some complicated board games are quite hard to learn, humans usually begin with playing on smaller boards and incrementally …

Board GamesGraph Neural NetworkIncremental Learning

AlphaZero Gomoku

2023-09-04 · Wen Liang, Chao Yu, Brian Whiteaker, Inyoung Huh 외

In the past few years, AlphaZero's exceptional capability in mastering intricate board games has garnered considerable interest. Initially designed for the game of Go, this revolutionary algorithm merges deep learning te…

Board GamesGame of Go

Impartial Games: A Challenge for Reinforcement Learning

2022-05-25 · Bei Zhou, Søren Riis

While AlphaZero-style reinforcement learning (RL) algorithms excel in various board games, in this paper we show that they face challenges on impartial games where players share pieces. We present a concrete example of a…

Board GamesPositionreinforcement-learningReinforcement Learning+1

Three-Head Neural Network Architecture for AlphaZero Learning

2019-09-25 · Chao GAO, Martin Mueller, Ryan Hayward, Hengshuai Yao 외

The search-based reinforcement learning algorithm AlphaZero has been used as a general method for mastering two-player games Go, chess and Shogi. One crucial ingredient in AlphaZero (and its predecessor AlphaGo Zero) is …