Improving Search with Supervised Learning in Trick-Based Card Games
원문 초록
In trick-taking card games, a two-step process of state sampling and evaluation is widely used to approximate move values. While the evaluation component is vital, the accuracy of move value estimates is also fundamentally linked to how well the sampling distribution corresponds the true distribution. Despite this, recent work in trick-taking card game AI has mainly focused on improving evaluation algorithms with limited work on improving sampling. In this paper, we focus on the effect of sampling on the strength of a player and propose a novel method of sampling more realistic states given move history. In particular, we use predictions about locations of individual cards made by a deep neural network --- trained on data from human gameplay - in order to sample likely worlds for evaluation. This technique, used in conjunction with Perfect Information Monte Carlo (PIMC) search, provides a substantial increase in cardplay strength in the popular trick-taking card game of Skat.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Optimizing Hearthstone Agents using an Evolutionary Algorithm
Identifying and Clustering Counter Relationships of Team Compositions in PvP Games for Efficient Balance Analysis
AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding
Enhancing Commentary Strategies for Imperfect Information Card Games: A Study of Large Language Models in Guandan Commentary
GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations
DanZero+: Dominating the GuanDan Game through Reinforcement Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.