Logo des Repositoriums

Künstliche Intelligenz 25(1) - März 2011

Autor*innen mit den meisten Dokumenten  

Auflistung nach:

Neueste Veröffentlichungen

1 - 10 von 20
  • Zeitschriftenartikel
    Knowledge-Based General Game Playing
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Haufe, Sebastian; Michulke, Daniel; Schiffel, Stephan; Thielscher, Michael
    Although we humans cannot compete with computers at simple brute-force search, this is often more than compensated for by our ability to discover structures in new games and to quickly learn how to perform highly selective, informed search. To attain the same level of intelligence, general game playing systems must be able to figure out, without human assistance, what a new game is really about. This makes General Game Playing in ideal testbed for human-level AI, because ultimate success can only be achieved if computers match our ability to master new games by acquiring and exploiting new knowledge. This article introduces five knowledge-based methods for General Game Playing. Each of these techniques contributes to the ongoing success of our FLUXPLAYER (Schiffel and Thielscher in Proceedings of the National Conference on Artificial Intelligence, pp. 1191–1196, 2007), which was among the top four players at each of the past AAAI competitions and in particular was crowned World Champion in 2006.
  • Zeitschriftenartikel
    Neue Bücher in der Reihe DISKI: Dissertationen zur Künstlichen Intelligenz Editor-in-Chief: Wolfgang Bibel
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Hertzberg, Joachim
    Hinweis 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.
  • Zeitschriftenartikel
    A GGP Feature Learning Algorithm
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Kirci, Mesut; Sturtevant, Nathan; Schaeffer, Jonathan
    This paper presents a learning algorithm for two-player, alternating move GGP games. The Game Independent Feature Learning algorithm, GIFL, uses the differences in temporally-related states to learn patterns that are correlated with winning or losing a GGP game. These patterns are then used to inform the search. GIFL is simple, robust and improves the quality of play in the majority of games tested. GIFL has been successfully used in the GGP program Maligne.
  • Zeitschriftenartikel
    Fusing DL Reasoning with HTN Planning
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Hartanto, Ronny
    Action planning has been used in the field of robotics for solving long-running tasks. However, the definition of a planning problem for a complex, real-world robot is not trivial. The planning process could become intractable as its search spaces become large. The dissertation presented in this article introduces a novel approach which amalgamates Description Logic (dl) reasoning with Hierarchical Task Network (htn) planning. The planning domain description as well as fundamental htn planning concepts are represented in dl and can therefore be subject to dl reasoning; from these representations, concise planning problems are generated for htn planning.
  • Zeitschriftenartikel
    CadiaPlayer: Search-Control Techniques
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Finnsson, Hilmar; Björnsson, Yngvi
    Effective 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.
  • Zeitschriftenartikel
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Thielscher, Michael
    The 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.
  • Zeitschriftenartikel
    1 Jahr KI bei Springer
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Schneeberger, Josef
  • Zeitschriftenartikel
    Using Decision Trees for State Evaluation in General Game Playing
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Sheng, Xinxin; Thuente, David
    A general game playing agent understands the formal descriptions of an arbitrary game in the multi-agent environment and learns to play the given games without human intervention. In this paper, we present an agent that automatically extracts common features shared by the game winners and uses such learned features to build decision trees to guide the heuristic search. We present data to show the significant performance improvements contributed by the decision tree evaluation. We also show by using hash tables in knowledge reasoning, our agent uses 80% less time when compared to a widely available GGP agent written in the same language.
  • Zeitschriftenartikel
    Strategy Generation and Evaluation for Meta-Game Playing
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Pell, Barney
  • Zeitschriftenartikel
    Reasoning about Time, Action and Knowledge in Multi-Agent Systems
    (KI - Künstliche Intelligenz: Vol. 25, No. 1, 2011) Ruan, Ji
    This 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.