Wyniki wyszukiwania - BazTech

1

A Practical Solution to Handling Randomness and Imperfect Information in Monte Carlo Tree Search

Świechowski Maciej, Tajmajer Tomasz

Annals of Computer Science and Information Systems

|

2021

|

Vol. 25

101--110

EN

This paper provides practical guidelines for developing strong AI agents based on the Monte Carlo Tree Search algorithm in a game with imperfect information and/or randomness. These guidelines are backed up by series of experiments carried out in the very popular game - Hearthstone. Despite the focus on Hearthstone, the paper is written with reusability and universal applications in mind. For MCTS algorithm, we introduced a few novel ideas such as complete elimination of the so-called nature moves, separation of decision and simulation states as well as a multi-layered transposition table. These have helped to create a strong Hearthstone agent.

2

Introducing LogDL - Log Description Language for Insights from Complex Data

Świechowski Maciej, Ślęzak Dominik

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

145--154

EN

We propose a new logic-based language called LogDL (Log Description Language) that is designed to be a medium for the knowledge discovery workflows conducted over multimodal process-related and spatio-temporal data sets. It makes it possible to operate with the original data along with machine-learning-driven insights expressed as facts, rules and formulas, regarded as higher-level descriptive logs reflecting knowledge about the observed processes in real or virtual environments. LogDL is inspired by the research at the border of AI and games, precisely by GDL (Game Description Language) that was developed for General Game Playing. We compare LogDL to GDL, emphasizing that formal frameworks for analyzing gameplay data sets are a good prerequisite for the case of real,``not digital'' processes. As LogDL is a logic-based language, we present its syntax and semantics. We also discuss how to design its high-performance interpreter that is a must for commercial scenarios.

3

Game AI Competitions: Motivation for the Imitation Game-Playing Competition

Świechowski Maciej

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

155--160

EN

Games have played crucial role in advancing research in Artificial Intelligence and tracking its progress. In this article, a new proposal for game AI competition is presented. The goal is to create computer players which can learn and mimic the behavior of particular human players given access to their game records. We motivate usefulness of such an approach in various aspects, e.g., new ways of understanding what constitutes the human-like AI or how well it fits into the existing game production workflows. This competition may integrate many problems such as learning, representation, approximation and compression of AI, pattern recognition, knowledge extraction etc. This leads to multi-directional implications both on research and industry. In addition to the proposal, we include a short survey of the available game AI competitions.