In Proceedings of the Twenty - First National Conference on Artificial Intelligence ( AAAI - 06 ) , Boston , MA , July 2006 . Automatic Heuristic Construction in a Complete General Game Player ∗

نویسندگان

  • Gregory Kuhlmann
  • Kurt Dresner
  • Peter Stone
چکیده

Computer game players are typically designed to play a single game: today’s best chess-playing programs cannot play checkers, or even tic-tac-toe. General Game Playing is the problem of designing an agent capable of playing many different previously unseen games. The first AAAI General Game Playing Competition was held at AAAI 2005 in order to promote research in this area. In this article, we survey some of the issues involved in creating a general game playing system and introduce our entry to that event. The main feature of our approach is a novel method for automatically constructing effective search heuristics based on the formal game description. Our agent is fully implemented and tested in a range of different games.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

AAAI's National and Innovative Applications Conferences Celebrate 50 Years of AI

For the AI researchers and practitioners who convened in Boston on July 16–20, 2006 for the AAAI sponsored Twenty-First National Conference on Artificial Intelligence (AAAI-06) and the Eighteenth Innovative Applications of AI Conference (IAAI-06), there was an atmosphere of celebration, collegiality, and continued innovation. The celebration of the first 50 years of AI began the previous week a...

متن کامل

Automatic Heuristic Construction in a Complete General Game Player

Computer game players are typically designed to play a single game: today’s best chess-playing programs cannot play checkers, or even tic-tac-toe. General Game Playing is the problem of designing an agent capable of playing many different previously unseen games. The first AAAI General Game Playing Competition was held at AAAI 2005 in order to promote research in this area. In this article, we ...

متن کامل

Reports on the Twenty-First National Conference on Artificial Intelligence (AAAI-06) Workshop Program

AAAI was pleased to present the AAAI-06 workshop program. Workshops were held Sunday and Monday, July 16–17, 2006, at the Seaport Hotel and World Trade Center in Boston, Massachusetts. The AAAI06 workshop program included 14 workshops covering a wide range of ■ The Workshop program of the TwentyFirst National Conference on Artificial Intelligence was held July 16–17, 2006 in Boston, Massachuset...

متن کامل

Strong Mediated Equilibrium

Stability against potential deviations by sets of agents is a most desired property in the design and analysis of multi-agent systems. However, unfortunately, this property is typically not satisfied. In game-theoretic terms, a strong equilibrium, which is a strategy profile immune to deviations by coalition, rarely exists. This paper suggests the use of mediators in order to enrich the set of ...

متن کامل

Celebrating AI's Fiftieth Anniversary and Continuing Innovation at the AAAI/IAAI-06 Conferences

today's keyboards. The introduction of the FORTRAN language was still a year away. " The summer conference, convened on the campus of Dartmouth College in Hanover, New Hampshire, brought together for the first time many of the early pioneers of cybernetics , automata and information theory , operations research, and game theory, " according to the Software History Dictionary Project of the Char...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2006