Auflistung nach:
Auflistung Künstliche Intelligenz 25(1) - März 2011 nach Erscheinungsdatum
1 - 10 von 20
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelExplizites Wissen versus Black Box Ansätze in der KI(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Puppe, FrankAngesichts der Erfolge statistischer Modelle, bei denen aus sehr großen Datenbeständen und sehr leistungsfähiger Hardware intelligente Programme generiert werden, stellt sich die Frage, ob es sich noch lohnt, menschliche Vorgehensweisen in der KI nachzubilden.
- ZeitschriftenartikelCenturio, a General Game Player: Parallel, Java- and ASP-based(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Möller, Maximilian; Schneider, Marius; Wegner, Martin; Schaub, TorstenWe present the General Game Playing system Centurio. Centurio is a Java-based player featuring different strategies based on Monte Carlo Tree Search extended by techniques borrowed from Upper Confidence bounds applied to Trees as well as Answer Set Programming (for single-player games). Centurio’s Monte Carlo Tree Search is accomplished in a massively parallel way by means of multi-threading as well as cluster-computing. Another major feature of Centurio is its compilation of game descriptions, states, and state manipulations into Java, yielding an edge over existing Prolog-based approaches. Centurio is open source software freely available via the web.
- ZeitschriftenartikelNews(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011)
- ZeitschriftenartikelCadiaPlayer: Search-Control Techniques(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Finnsson, Hilmar; Björnsson, YngviEffective search control is one of the key components of any successful simulation-based game-playing program. In General Game Playing (GGP), learning of useful search-control knowledge is a particularly challenging task because it must be done in real-time during online play. In here we describe the search-control techniques used in the 2010 version of the GGP agent CadiaPlayer, and show how they have evolved over the years to become increasingly effective and robust across a wide range of games. In particular, we present a new combined search-control scheme (RAVE/MAST/FAST) for biasing action selection. The scheme proves quite effective on a wide range of games including chess-like games, which have up until now proved quite challenging for simulation-based GGP agents.
- ZeitschriftenartikelGDL-II(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Thielscher, MichaelThe Game Description Language (GDL) used in the past AAAI competitions allows to tell a system the rules of arbitrary finite games that are characterised by perfect information, but does not extend to games in which players have asymmetric information, e.g. about their own hand of cards, or which involve elements of chance like the roll of dice. Accordingly, contemporary general game-playing systems are not designed to play games such as Backgammon, Poker or Diplomacy. GDL-II (for: GDL with Incomplete/Imperfect Information) is a recent extension of the original description language that makes general game playing truly general, because it allows to describe just any finite game with arbitrary forms of randomness as well as imperfect/incomplete information. This brings along the challenge to build the next generation of truly general game-playing systems that are able to understand any game description given in GDL-II and to learn to master these types of games, too.
- ZeitschriftenartikelA Parallel General Game Player(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Méhat, Jean; Cazenave, TristanWe have parallelized our general game player Ary on a cluster of computers. We propose multiple parallelization algorithms. For the sake of simplicity all our algorithms have processes that run independently and that join their results at the end of the thinking time in order to choose a move. Parallelization works very well for checkers, quite well for other two player sequential move games and not at all for a few other games.
- ZeitschriftenartikelAgreement Computing(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Sierra, Carles; Botti, Vicent; Ossowski, SaschaIn this paper we introduce the concept of Agreement Computing, motivate the central role that the concept of agreement plays in open software systems and discuss a number of research challenges that need to be addressed to make the agreement computing vision a reality.
- ZeitschriftenartikelStrategy Generation and Evaluation for Meta-Game Playing(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Pell, Barney
- ZeitschriftenartikelReasoning about Time, Action and Knowledge in Multi-Agent Systems(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Ruan, JiThis thesis is in the area of Multi-Agent Systems (MASs). In a MAS, multiple agents act on their own behalf or of other stakeholders, and key issues here are that they are situated, intelligent, rational and social. They are situated in the sense that they need to be able to sense their environment, intelligent in the sense that they need to model the world around them and make decisions in time and with incomplete information, rational in the sense that they make strategic deliberations when pursuing their own interest, and social in the sense that they are aware of other agents, and their level of intelligence, rationality and social skills. The General Game Playing competition tests the ability of multiple autonomous game playing agents on achieving pre-defined goals. In order to build such agents, one needs to study how agents can represent knowledge (or information) about the world, how their actions may change the world and how a MAS evolves over time due to actions performed by agents. We provide a logic-based account for the specification and verification of MASs, in terms of time, action and knowledge. The contributions are divided into two research themes.The full dissertation can be downloaded at http://ac.jiruan.net/thesis.
- ZeitschriftenartikelNeue Bücher in der Reihe DISKI: Dissertationen zur Künstlichen Intelligenz Editor-in-Chief: Wolfgang Bibel(KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Hertzberg, JoachimHinweis der Herausgeber der KI-Zeitschrift: Je ein freies Rezensionsexemplare der Bände der DISKI-Reihe können bei den Herausgebern angefordert werden unter der Voraussetzung, dass eine Rezension anschließend für die KI-Zeitschrift geschrieben wird. Zu Umfang und Form von Rezensionen siehe die entsprechenden Autorenhinweise.