DeepAI AI Chat
Log In Sign Up

Method for Constructing Artificial Intelligence Player with Abstraction to Markov Decision Processes in Multiplayer Game of Mahjong

by   Moyuru Kurita, et al.

We propose a method for constructing artificial intelligence (AI) of mahjong, which is a multiplayer imperfect information game. Since the size of the game tree is huge, constructing an expert-level AI player of mahjong is challenging. We define multiple Markov decision processes (MDPs) as abstractions of mahjong to construct effective search trees. We also introduce two methods of inferring state values of the original mahjong using these MDPs. We evaluated the effectiveness of our method using gameplays vis-à-vis the current strongest AI player.


page 1

page 2

page 3

page 4


Gomoku: analysis of the game and of the player Wine

Gomoku, also known as five in a row, is a classical board game, ideally ...

Participation Interfaces for Human-Centered AI

Emerging artificial intelligence (AI) applications often balance the pre...

Toward Solving 2-TBSG Efficiently

2-TBSG is a two-player game model which aims to find Nash equilibriums a...

Strategies for the Iterated Prisoner's Dilemma

We explore some strategies which tend to perform well in the IPD. We sta...

Counterexample-guided Planning

Planning in adversarial and uncertain environments can be modeled as the...

Constructing Abstraction Hierarchies Using a Skill-Symbol Loop

We describe a framework for building abstraction hierarchies whereby an ...

Game State Learning via Game Scene Augmentation

Having access to accurate game state information is of utmost importance...