Filters








32 Hits in 0.56 sec

Helping AI to Play Hearthstone: AAIA'17 Data Mining Challenge [article]

Andrzej Janusz, Maciej Świechowski, Tomasz Tajmajer
2017 arXiv   pre-print
This paper summarizes the AAIA'17 Data Mining Challenge: Helping AI to Play Hearthstone which was held between March 23, and May 15, 2017 at the Knowledge Pit platform. We briefly describe the scope and background of this competition in the context of a more general project related to the development of an AI engine for video games, called Grail. We also discuss the outcomes of this challenge and demonstrate how predictive models for the assessment of player's winning chances can be utilized in
more » ... a construction of an intelligent agent for playing Hearthstone. Finally, we show a few selected machine learning approaches for modeling state and action values in Hearthstone. We provide evaluation for a few promising solutions that may be used to create more advanced types of agents, especially in conjunction with Monte Carlo Tree Search algorithms.
arXiv:1708.00730v1 fatcat:mdopofdmobgxfffobq7sk4ixoe

Improving Hearthstone AI by Combining MCTS and Supervised Learning Algorithms [article]

Maciej Świechowski, Tomasz Tajmajer, Andrzej Janusz
2018 arXiv   pre-print
We investigate the impact of supervised prediction models on the strength and efficiency of artificial agents that use the Monte-Carlo Tree Search (MCTS) algorithm to play a popular video game Hearthstone: Heroes of Warcraft. We overview our custom implementation of the MCTS that is well-suited for games with partially hidden information and random effects. We also describe experiments which we designed to quantify the performance of our Hearthstone agent's decision making. We show that even
more » ... ple neural networks can be trained and successfully used for the evaluation of game states. Moreover, we demonstrate that by providing a guidance to the game state search heuristic, it is possible to substantially improve the win rate, and at the same time reduce the required computations.
arXiv:1808.04794v1 fatcat:e5jyvgibirdyrndx3c5or4jzpu

Generic Heuristic Approach to General Game Playing [chapter]

Jacek Mańdziuk, Maciej Świechowski
2012 Lecture Notes in Computer Science  
General Game Playing (GGP) is a specially designed environment for creating and testing competitive agents which can play variety of games. The fundamental motivation is to advance the development of various artificial intelligence methods operating together in a previously unknown environment. This approach extrapolates better on real world problems and follows artificial intelligence paradigms better than dedicated single-game optimized solutions. This paper presents a universal method of
more » ... tructing the heuristic evaluation function for any game playable within the GGP framework. The algorithm embraces distinctive discovery of candidate features to be included in the evaluation function and learning their correlations with actions performed by the players and the game score. Our method integrates well with the UCT algorithm which is currently the state-of-the-art approach in GGP.
doi:10.1007/978-3-642-27660-6_53 fatcat:bpcal7ooczfhdleajy5b2yompe

Recent Advances in General Game Playing

Maciej Świechowski, HyunSoo Park, Jacek Mańdziuk, Kyung-Joong Kim
2015 The Scientific World Journal  
The goal of General Game Playing (GGP) has been to develop computer programs that can perform well across various game types. It is natural for human game players to transfer knowledge from games they already know how to play to other similar games. GGP research attempts to design systems that work well across different game types, including unknown new games. In this review, we present a survey of recent advances (2011 to 2014) in GGP for both traditional games and video games. It is notable
more » ... at research on GGP has been expanding into modern video games. Monte-Carlo Tree Search and its enhancements have been the most influential techniques in GGP for both research domains. Additionally, international competitions have become important events that promote and increase GGP research. Recently, a video GGP competition was launched. In this survey, we review recent progress in the most challenging research areas of Artificial Intelligence (AI) related to universal game playing.
doi:10.1155/2015/986262 pmid:26380375 pmcid:PMC4561326 fatcat:teennjh5ybepfp33o33o3pwmkm

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

Maciej Świechowski
2020 Proceedings of the 2020 Federated Conference on Computer Science and Information Systems  
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
more » ... on 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.
doi:10.15439/2020f126 dblp:conf/fedcsis/Swiechowski20 fatcat:abhgqzwgrfaofd5sttasw3baae

Introducing LogDL - Log Description Language for Insights from Complex Data

Maciej Świechowski, Dominik Ślęzak
2020 Proceedings of the 2020 Federated Conference on Computer Science and Information Systems  
We propose a new logic-based language called Log Description Language (LogDL), designed to be a medium for the knowledge discovery workflows over complex data sets. It makes it possible to operate with the original data along with machinelearning-driven insights expressed as facts and rules, regarded as so-called descriptive logs characterizing the observed processes in real or virtual environments. LogDL is inspired by the research at the border of AI and games, precisely by Game Description
more » ... nguage (GDL) that was developed for General Game Playing (GGP). We emphasize that such formal frameworks for analyzing the gameplay data are a good prerequisite for the case of real, "not digital" processes. We also refer to Fogs of War (FoW)our upcoming project related to AI in video games with limited information -whereby LogDL will be used as well.
doi:10.15439/2020f168 dblp:conf/fedcsis/SwiechowskiS20 fatcat:72yp5jsxdvd4zdjzz6j7y76gyu

Helping AI to Play Hearthstone: AAIA'17 Data Mining Challenge

Andrzej Janusz, Tomasz Tajmajer, Maciej Świechowski
2017 Proceedings of the 2017 Federated Conference on Computer Science and Information Systems  
This paper summarizes the AAIA'17 Data Mining Challenge: Helping AI to Play Hearthstone which was held between March 23, and May 15, 2017 at the Knowledge Pit platform. We briefly describe the scope and background of this competition in the context of a more general project related to the development of an AI engine for video games, called Grail. We also discuss the outcomes of this challenge and demonstrate how predictive models for the assessment of player's winning chances can be utilized in
more » ... a construction of an intelligent agent for playing Hearthstone. Finally, we show a few selected machine learning approaches for modeling state and action values in Hearthstone. We provide evaluation for a few promising solutions that may be used to create more advanced types of agents, especially in conjunction with Monte Carlo Tree Search algorithms.
doi:10.15439/2017f573 dblp:conf/fedcsis/JanuszTS17 fatcat:f6uej5xfvzarvfryptjgetkd5u

Monte Carlo Tree Search: A Review of Recent Modifications and Applications [article]

Maciej Świechowski, Konrad Godlewski, Bartosz Sawicki, Jacek Mańdziuk
2022 arXiv   pre-print
Świechowski et al. (2018) use the MCTS algorithm together with supervised learning for the game of Hearthstone.  ...  The method was further extended towards handling single-player games more efficiently (Świechowski et al., 2016) .  ...  Root-Tree Parallelization The approach proposed by Świechowski and Mańdziuk (2016a) defines a way of combining Root-and Tree Parallelization algorithms that leads to a very high scalability.  ... 
arXiv:2103.04931v3 fatcat:xvkkhhk2czhhxmcbueagtccnam

Toward an Intelligent HS Deck Advisor: Lessons Learned from AAIA'18 Data Mining Competition

Andrzej Janusz, Tomasz Tajmajer, Maciej Świechowski, Łukasz Grad, Jacek Puczniewski, Dominik Ślęzak
2018 Proceedings of the 2018 Federated Conference on Computer Science and Information Systems  
We summarize AAIA'18 Data Mining Competition organized at the Knowledge Pit platform. We explain the competition's scope and outline its results. We also review several approaches to the problem of representing Hearthstone decks in a vector space. We divide such approaches into categories based on a type of the data about individual cards that they use. Finally, we outline experiments aiming to evaluate usefulness of various deck representations for the task of win-rates prediction.
doi:10.15439/2018f386 dblp:conf/fedcsis/JanuszTSGPS18 fatcat:sjqavfyss5ggdcpvhtyazd2lya

Human-Machine Cooperation in General Game Playing

Maciej´swiechowski Maciej´swiechowski, Kathryn Merrick, Jacek Ma´ndziuk, Hussein Abbass
unpublished
Świechowski  ... 
fatcat:lducune5l5fttn7s7lcod2atbm

Human-Machine Cooperation Loop in Game Playing

Maciej´swiechowski Maciej´swiechowski, Kathryn Merrick, Jacek Ma´ndziukma´ndziuk, Hussein Abbass
International Journal on Advances in Intelligent Systems   unpublished
This paper presents a new concept for human-machine iterative cooperation based on the Upper Confidence Bounds Applied to Trees method. Analysis of such human-computer cooperation may potentially lead to pertinent insights related to performance improvement of both the human subject and an artificial agent (machine) during certain kinds of strategic interactions. While the experiments described in this paper refer to the so-called General Game Playing (being a certain embodiment of multi-game
more » ... aying) the overall idea of proposed human-machine cooperation loop extends beyond game domain and can, in principle, be implemented in the form of a flexible general-purpose system applicable to cooperative problem solving or strategic interactions of various kinds. The concept proposed in this study is evaluated by means of a direct involvement of human subjects in specifically defined cooperative environment, which provides vast opportunity to learn from and cooperate with an artificial game playing agent under the certain rules of cooperation. The choice of games is seemingly important to this kind of experiment. Although the participants played better with the assistance of the machine in some of the games, they lost the track in subsequent matches when the assistance was (intentionally) no longer available. Possible reasons for such an activity pattern are discussed in the conclusions. Three design iterations showing evolution of the experiment setup are presented in the paper. The analysis of cooperative and non-cooperative matches reveals different patterns for each chosen game characterized by various levels of advantage gained by means of cooperation.
fatcat:uuwfvyrhgzaf7jdk7ct3a37jue

A Crossover That Matches Diverse Parents Together in Evolutionary Algorithms [article]

Maciej Świechowski
2021 pre-print
Crossover and mutation are the two main operators that lead to new solutions in evolutionary approaches. In this article, a new method of performing the crossover phase is presented. The problem of choice is evolutionary decision tree construction. The method aims at finding such individuals that together complement each other. Hence we say that they are diversely specialized. We propose the way of calculating the so-called complementary fitness. In several empirical experiments, we evaluate
more » ... efficacy of the method proposed in four variants and compare it to a fitness-rank-based approach. One variant emerges clearly as the best approach, whereas the remaining ones are below the baseline.
doi:10.1145/3449726.3459431 arXiv:2105.03680v1 fatcat:wqskqzvwqja2pcwdjn25iescay

Historia budowlana późnoromańskiego kościoła w Tulcach koło Poznania w świetle badań architektonicznych

Karolina Zimna-Kawecka, Maciej Prarat
2018 Acta Universitatis Nicolai Copernici Zabytkoznawstwo i Konserwatorstwo  
Maciej Prarat, Karolina Zimna-Kawecka, 2014 1 Zob. podstawową w tym zakresie, wielokrotnie wznawianą pracę: Zygmunt Świechowski, Katalog architektury romańskiej w Polsce (Warszawa: Wydawnictwo  ...  Świechowski, Architektura, [56] [57] Zachwatowicz, "Architektura", 192. 33 Świechowski, Architektura, [225] [226] .  ... 
doi:10.12775/aunc_zik.2017.001 fatcat:hiysu2zskjevrfrbteydnlkgge

Page 563 of National Union Catalog Vol. 43, Issue [page]

1958 National Union Catalog  
Kolegiata Swietego Marcl' NA5691.89 60-33183 Swiechowski, Zygmunt, Z dziejéw Stupska i Ustki. (By, Z. Swiechowski & J. Mertka. Poznafi ;Wydawn.  ...  PJ5008.S85 58-52426 Maciej. Instytucje polskiego prawa pracy w latach 1918-1939. iWyd. 1. Warszawa, A well Wydawn. Naukowe, ,1960, . 24cm.  ... 

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

Maciej Świechowski, Tomasz Tajmajer
2021 Proceedings of the 16th Conference on Computer Science and Intelligence Systems   unpublished
 SWIECHOWSKI, TOMASZ TAJMAJER: A PRACTICAL SOLUTION TO HANDLING RANDOMNESS AND IMPERFECT INFORMATION 109 PROCEEDINGS OF THE FEDCSIS.  ...   SWIECHOWSKI, TOMASZ TAJMAJER: A PRACTICAL SOLUTION TO HANDLING RANDOMNESS AND IMPERFECT INFORMATION the hidden information in the game: the hand and the secret zone.  ... 
doi:10.15439/2021f3 fatcat:u6q6qcozd5aj3ncjzrfxnemk4e
« Previous Showing results 1 — 15 out of 32 results