Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Dap Hartmann is active.

Publication


Featured researches published by Dap Hartmann.


ICGA Journal | 2017

Let's Catch the Train to Monte-Carlo

Dap Hartmann

While Monte-Carlo Tree Search (MCTS) has successfully been implemented in many games, its effectiveness appears to be greatest in the game of Go. In this thesis, Hendrik Baier even earmarks MCTS “the dominating paradigm in the challenging field of computer Go.” Having mentioned Go, there is no escaping linking another statement from this thesis to the recent astonishing accomplishment by DeepMind’s AlphaGo. It illustrates how fast computer game playing is currently improving – irrespective of whether you call that Artificial Intelligence or not. In Section 3.2.1, Baier writes: “the world’s best human Go players are still superior to the best computer programs, and writing a master strength Go program stands as a grand challenge of AI.” Four months after Hendrik Baier defended this PhD thesis, AlphaGo convincingly beat Lee Sedol 4-1. Lee is considered to be the best Go player in the world over the last decade.2 A magnificent achievement indeed, but let us not forget that it is the culmination of all the hard work over the past decades of a great many computer games researchers who have contributed to this monumental victory. One of the three pillars on which rests the success of AlphaGo is MCTS, the topic of this thesis. It would be interesting to know whether AlphaGo contains any of the MCTS enhancements that Hendrik Baier describes in this thesis or in any of his scientific papers. The oldest paper I could find (Baier and Drake, 2010), was published in the IEEE Transactions on Computational Intelligence in 2010, and describes an improvement to the Last-Good-Reply Policy in Monte Carlo Go.


ICGA Journal | 2014

A Statue of Unremitting Devotion

Dap Hartmann

This book contains 21 selected and revised papers of the 8th Computers and Games Conference (CG 2013) which was held in Yokohama, Japan from August 13-15. Since CG2004 in Ramat-Gan, the World Computer Chess Championship has been organized in conjunction with the Computers and Games conference (or vice versa). Yokohama witnessed the 20 edition of this major event since the legendary tournament in Stockholm in 1974 where KAISSA won all four games and became the first computer chess world champion. In Yokohama, JUNIOR prolonged its title in a field of only 6 participants. That was the lowest attendance ever, and maybe reason for some concern. In Stockholm, 40 years ago, 13 programs were competing, and this number steadily climbed every next tournament until 1999 when the 9 WCCC in Paderborn saw no less than 30 participants. Since then, the attendance has gradually dropped to 9 participants in Tilburg (2011) and now only 6 in Yokohama. The upshot of this trend is that for the first time a round-robin tournament could be played, surely the best way to determine the strongest program. Nevertheless, let us hope that the upcoming championship in Leiden next year, will attract more competitors. Yokohama was also the venue for the 17th Computer and Games Tournament, formerly knowns as the Computer Olympiad, which hosted 21 games. In all three Go events (9x9, 13x13 and 19x19) ZEN, brainchild of Yoji Ojima and Hideki Kato, prolonged their Olympic gold medals from Tilburg by winning all but one game. Unfortunately, as far as I am aware, the authors of ZEN have never published anything on their approach to computer Go. Of course they want to stay ahead of the competition, but as they probably have benefitted from the published work of others, I would recommend them to give something back to the community. Hence, I am looking forward to the next Computers and Games Conference in the hope that the program committee will persuade approach Ojima and Kato to share some of their wisdom with us. If that does not work, maybe an in-depth interview with probing questions by a computer Go expert is an option.


ICGA Journal | 2004

THE TENTH COMMANDMENT

Dap Hartmann

Make more knowledge even in less time every day. You may not always spend your time and money to go abroad and get the experience and knowledge by yourself. Reading is a good alternative to do in getting this desirable knowledge and experience. You may gain many things from experiencing directly, but of course it will spend much money. So here, by reading the tenth commandment, you can take more advantages with limited budget.


ICGA Journal | 2003

BEHIND DEEP BLUE

Dap Hartmann


ICGA Journal | 2000

GAMES IN AI RESEARCH

Dap Hartmann


ICGA Journal | 2002

CHIPS CHALLENGING CHAMPIONS

Dap Hartmann


ICGA Journal | 1987

How to Extract Relevant Knowledge from Grandmaster Games

Dap Hartmann


ICGA Journal | 1987

How to Extract Relevant Knowledge from Grandmaster Games: PART 2: The Notion of Mobility, and the Work of De Groot and Slater

Dap Hartmann


ICGA Journal | 1987

How to Extract Relevant Knowledge from Grandmaster Games: Part 1: Grandmasters have insights – the problem is what to incorporate into practical programs

Dap Hartmann


ICGA Journal | 2007

ON THE IMPORTANCE OF SELF-CONTAINED PAPERS

Dap Hartmann

Collaboration


Dive into the Dap Hartmann's collaboration.

Top Co-Authors

Avatar
Researchain Logo
Decentralizing Knowledge