8,272 Hits in 5.0 sec

Using Heuristic-Search Based Engines for Estimating Human Skill at Chess

Matej Guid, Ivan Bratko
2011 ICGA Journal  
Establishing heuristic-search based chess programs as appropriate tools for estimating human skill levels at chess may seem impossible due to the following issues: the programs' evaluations and decisions  ...  any of these programs at various levels of search.  ...  Our approach is different: we assess skill level at chess by applying chess engines to analyse particular positions and moves played.  ... 
doi:10.3233/icg-2011-34204 fatcat:yorbdjh5trd3dpwvqyvfbx3z6m

Learning Personalized Models of Human Behavior in Chess [article]

Reid McIlroy-Young, Russell Wang, Siddhartha Sen, Jon Kleinberg, Ashton Anderson
2021 arXiv   pre-print
Furthermore, we can accurately perform stylometry -- predicting who made a given set of actions -- indicating that our personalized models capture human decision-making at an individual level.  ...  Even when machine learning systems surpass human ability in a domain, there are many reasons why AI systems that capture human-like behavior would be desirable: humans may want to learn from them, they  ...  By training several models, each on a subset of games limited to a coarse skill level, this approach captures human behavior in chess at different levels of strength.  ... 
arXiv:2008.10086v2 fatcat:p52f5u2qgzb7lcomfxrcs6tabu


Matej Guid, Ivan Bratko
2006 ICGA Journal  
In this contribution, we attempt to make such a comparison. It is based on the evaluation of the games played by the World Chess Champions in their championship matches.  ...  Overall, the results can be nicely interpreted by a chess expert.  ...  To retain the style of human play, we chose to use for this experiment games played between these top programs against top human players.  ... 
doi:10.3233/icg-2006-29203 fatcat:mkwrihom5fdqbmte7w3cpg36w4

Aligning Superhuman AI and Human Behavior: Chess as a Model System [article]

Reid McIlroy-Young and Siddhartha Sen and Jon Kleinberg and Ashton Anderson
2020 arXiv   pre-print
The hundreds of millions of games played online by players at every skill level form a rich source of data in which these decisions, and their exact context, are recorded in minute detail.  ...  We develop and introduce Maia, a customized version of Alpha-Zero trained on human chess games, that predicts human moves at a much higher accuracy than existing engines, and can achieve maximum accuracy  ...  Programming a computer to play chess at a high level was a long-standing holy grail of artificial intelligence, and superhuman play was definitively achieved by 2005 (point (i)).  ... 
arXiv:2006.01855v1 fatcat:ciyqt6rsqva3hfnmxsrtgzv5sy

Simulating human grandmasters

Omid David-Tabibi, H. Jaap van den Herik, Moshe Koppel, Nathan S. Netanyahu
2009 Proceedings of the 11th Annual conference on Genetic and evolutionary computation - GECCO '09  
This paper demonstrates the use of genetic algorithms for evolving a grandmaster-level evaluation function for a chess program. This is achieved by combining supervised and unsupervised learning.  ...  While past attempts succeeded in creating a grandmaster-level program by mimicking the behavior of existing computer chess programs, this paper presents the first successful attempt at evolving a state-of-the-art  ...  grandmaster-level chess program.  ... 
doi:10.1145/1569901.1570100 dblp:conf/gecco/David-TabibiHKN09 fatcat:eqp2jhqgejcqngxib5p3dm5uiu

A Methodology for Learning Players' Styles from Game Records [article]

Mark Levene, Trevor Fenner
2009 arXiv   pre-print
We describe a preliminary investigation into learning a Chess player's style from game records.  ...  by trying to detect who was playing white and who was playing black.  ...  Since methods used in the domain of Chess frequently transfer to other strategic board games, it would be interesting to try our approach on games such as Checkers and Go.  ... 
arXiv:0904.2595v1 fatcat:75stvsexpzfqpm2mphezzkuffu

Rating Super Constellation

D.E. Welsh
1985 ICGA Journal  
SC IS SUPER-CUNNING Super Constellation has a relatively "human" style and many of the games in the event were quite well-played, with relatively little of the weird nonsense that has too often characterized  ...  These annotations have been provided to the manufacturer as part of the rating service; such an arrangement is a novel and desirable form of employing proressional chess-players, with high-level promises  ... 
doi:10.3233/icg-1985-8214 fatcat:55im5ei6sfdxpoufvbn5dnnf4q


Dušan Veličković, Dragan Radovanović
2018 Facta Universitatis Series Physical Education and Sport  
Women are underrepresented and underperformanced in chess at the top level.  ...  Women generally score lower than men both on aggressiveness and dominance and at the same time during a chess game, mental fatigue occurs earlier in women.  ...  Women chess players show lower chess-specific self-esteem and choose a more defensive style when playing with males.  ... 
doi:10.22190/fupes180926032v fatcat:5ccus7jqzzhjbmryawou6d42lq

The ACM's 16th North American Computer-Chess Championship

Ken Thompson
1985 ICGA Journal  
Participants are required to attend a meeting at 12 noon on Sunday, October 13, for the purpose of officially registering for the tournament. Rules will be discussed at the meeting.  ...  Each entry is a computing system. A listing of all programs running on that system should be available on demand to the tournament director.  ...  The first and second rounds will be played Sunday, October 13th, at I PM and 7:30 PM.  ... 
doi:10.3233/icg-1985-8215 fatcat:bcwrx73oivcrxcurdekxtkccyi

Innovative Opening-Book Handling [chapter]

Chrilly Donninger, Ulf Lorenz
2006 Lecture Notes in Computer Science  
The best chess programs have reached the top level players in the human chess world.  ...  The so called opening books, which are databases containing thousands of Grandmaster games, have been seen as a big advantage of programs over humans, because the computers do never forget a variation.  ...  Before, between 1940 and 1970, programmers attempted to mimic human chess style, but the resulting programs were weak.  ... 
doi:10.1007/11922155_1 fatcat:kgoyuqae7zhivelf7kmqqv3zcm

Machine learning and games

Michael Bowling, Johannes Fürnkranz, Thore Graepel, Ron Musick
2006 Machine Learning  
For example, in Massive Multiplayer Online Role-playing Games (MMORGs) an avatar that is trained to simulate a user's game-playing behavior could take his creator's place at times when the human player  ...  This requires building highly adaptive models that can substantively personalize to adversaries or partners with a wide range of competence and rapid shifts in play style.  ... 
doi:10.1007/s10994-006-8919-x fatcat:yzcw44fiards3dibi75vcgwcdi

Chess as a Testing Grounds for the Oracle Approach to AI Safety [article]

James D. Miller, Roman Yampolskiy, Olle Haggstrom, Stuart Armstrong
2020 arXiv   pre-print
This paper proposes a possibly practical means of using machine learning to create two classes of narrow AI oracles that would provide chess advice: those aligned with the player's interest, and those  ...  that want the player to lose and give deceptively bad advice.  ...  Anecdotally, it seems also that AlphaZero's style of play has already had some influence on top-level human play, such as with an increased propensity to h-pawn thrusts.  ... 
arXiv:2010.02911v1 fatcat:kya3crxpmvfzxgxalaakszsmoe

Page 680 of Journal of the Royal Anthropological Institute Vol. 19, Issue 3 [page]

2013 Journal of the Royal Anthropological Institute  
It is not about a group of people who play chess, and hc w they use the game to work through their relationships, extend or sever their connections to others.  ...  , desirous, bewitching, maddening’, and finally, in a reversal of the move from game to life: ‘Life is touch move’.  ... 

Field creativity and post-anthropocentrism

Stanislav Roudavski
2016 Digital Creativity  
The narrative on chess is intermitted by a section "on creativity" that attempts to contextualize the case-based discussion in the wider context and to consider motivations and implications.  ...  This article is an elaboration of such questions as well as an attempt at a partial response.  ...  For a human, being good at chess is to a large extent a challenge in pattern recognition. Very new ideas are increasingly rare, especially at the highest levels of play.  ... 
doi:10.1080/14626268.2016.1151443 fatcat:tihkscew35bmvjelw66wr6kftq


Fernand Gobet
2001 ICGA Journal  
Simon's interest in computer chess was clearly motivated by his desire to understand the mechanisms of human thought, and not by ambitions to develop strong programs per se.  ...  With colleagues at Carnegie Mellon, he worked on several computer models of chess players' perception and memory, such as PERCEIVER, MAPP, and CHREST.  ... 
doi:10.3233/icg-2001-24118 fatcat:t2w5zud3rrgyznq2inapalx2r4
« Previous Showing results 1 — 15 out of 8,272 results