Fast and Knowledge-Free Deep Learning for General Game Playing (Student Abstract)

2023-12-21 · Michał Maras, Michał Kępa, Jakub Kowalski, Marek Szykuła

We develop a method of adapting the AlphaZero model to General Game Playing (GGP) that focuses on faster model generation and requires less knowledge to be extracted from the game rules. The dataset generation uses MCTS playing instead of self-play; only the value network is used, and attention layers replace the convolutional ones. This allows us to abandon any assumptions about the action space and board topology. We implement the method within the Regular Boardgames GGP system and show that we can build models outperforming the UCT baseline for most games efficiently.

📄 PDF Abstract BibTeX arXiv:2312.14121

Code (0)

등록된 구현이 없습니다.

Tasks

Dataset Generation

Methods 이 논문이 사용한 방법론

AlphaZero AlphaZero is a reinforcement learning agent for playing board games such as Go, chess, and shogi.

Efficient Reasoning in Regular Boardgames

2020-06-15 · Jakub Kowalski, Radosław Miernik, Maksymilian Mika, Wojciech Pawlik 외

We present the technical side of reasoning in Regular Boardgames (RBG) language -- a universal General Game Playing (GGP) formalism for the class of finite deterministic games with perfect information, encoding rules in …

General Board Game Playing for Education and Research in Generic AI Game Learning

2019-07-11 · Wolfgang Konen

We present a new general board game (GBG) playing and learning framework. GBG defines the common interfaces for board games, game states and their AI agents. It allows one to run competitions of different agents on diffe…

Board Games

Playing a Strategy Game with Knowledge-Based Reinforcement Learning

2019-08-15 · Viktor Voss, Liudmyla Nechepurenko, Dr. Rudi Schaefer, Steffen Bauer

This paper presents Knowledge-Based Reinforcement Learning (KB-RL) as a method that combines a knowledge-based approach and a reinforcement learning (RL) technique into one method for intelligent problem solving. The pro…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

The Ludii Game Description Language is Universal

2022-05-01 · Dennis J. N. J. Soemers, Éric Piette, Matthew Stephenson, Cameron Browne

There are several different game description languages (GDLs), each intended to allow wide ranges of arbitrary games (i.e., general games) to be described in a single higher-level language than general-purpose programmin…

Split Moves for Monte-Carlo Tree Search

2021-12-14 · Jakub Kowalski, Maksymilian Mika, Wojciech Pawlik, Jakub Sutowicz 외

In many games, moves consist of several decisions made by the player. These decisions can be viewed as separate moves, which is already a common practice in multi-action games for efficiency reasons. Such division of a p…