Poker is an interesting test-bed for arti cial intelligence research. It is a game of imperfect information, where multiple competing agents must deal with probabilistic knowledge, risk assessment, and possible deception, not unlike decisions made in the real world. Opponent modeling is another dicult problem in decision-making applications, and it is essential to achieving high performance in poker. This paper describes the design considerations and architecture of the poker program Poki. In addition to methods for hand evaluation and betting strategy, Poki uses learning techniques to construct statistical models of each opponent, and dynamically adapts to exploit observed patterns and tendencies. The result is a program capable of playing reasonably strong poker, but there remains considerable research to be done to play at a world-class level. 1

Applications of fuzzy logic in heuristic control have been highly successful, but which aspects of fuzzy logic are essential to its practical usefulness? This paper shows that an apparently reasonable version of fuzzy logic collapses mathematically to two-valued logic. Moreover, there are few if any published reports of expert systems in real-world use that reason about uncertainty using fuzzy logic. It appears that the limitations of fuzzy logic have not been detrimental in control applications because current fuzzy controllers are far simpler than other knowledge-based systems. In the future, the technical limitations of fuzzy logic can be expected to become important in practice, and work on fuzzy controllers will also encounter several problems of scale already known for other knowledge-based systems. 1

Learning and Problem Solving with Multilayer Connectionist Systems September 1986 Charles William Anderson B.S., University of Nebraska M.S., University of Massachusetts Ph.D., University of Massachusetts Directed by: Professor Andrew G. Barto The di#culties of learning in multilayered networks of computational units has limited the use of connectionist systems in complex domains. This dissertation elucidates the issues of learning in a network's hidden units, and reviews methods for addressing these issues that have been developed through the years. Issues of learning in hidden units are shown to be analogous to learning issues for multilayer systems employing symbolic representations.

A model for learning systems is presented, and representative AI, pattern recognition, and control systems are discussed in terms of its framework. The model details the functional components felt to be essential for any learning system, independent of the techniques used for its construction, and the specific environment in which it operates. These components are erformance element, instance selector, critic, P earning element, blackboard, and world model. Consideration of learning system design leads naturally to the concept of a layered system, each layer operating at a different level of abstraction. Descriptive Terms: adaptation, learning, conceptformatIon, induct ion, performance element, instance selector, critic, learning element, blackboard, world model, multi-layered systems. 1

Poker is an interesting test-bed for artificial intelligence research. It is a game of imperfect knowledge, where multiple competing agents must deal with risk management, opponent modeling, unreliable information, and deception, much like decision-making applications in the real world. Opponent modeling is one of the most difficult problems in decision-making applications and in poker it is essential to achieving high performance. This paper describes and evaluates the implicit and explicit learning in the poker program Loki. Loki implicitly "learns" sophisticated strategies by selectively sampling likely cards for the opponents and then simulating the remainder of the game. The program has explicit learning for observing its opponents, constructing opponent models and dynamically adapting its play to exploit patterns in the opponents' play. The result is a program capable of playing reasonably strong poker, but there remains considerable research to be done to pl...

Artificial intelligence research has had great success in many clasic games such as chess, checkers, and othello. In these perfect-information domains, alpha-beta search is sufficient to achieve a high level of play. However Artificial intelligence research has long been criticized for focusing on deterministic domains of perfect information -- many problems in the real world exhibit properties of imperfect or incomplete information and non-determinism. Poker, the archetypal game studied by...

The program INDUCE 3 is a general-purpose inductive learning program that transforms symbolic descriptionsof real world event into more general or more useful descriptions of those events. The program produces such descriptions by performing various generalizing and simplifying tranformations on the input description-, under the guidance of criteria specified by the user. Many of these transformations are built into the program, others are supplied by the user.

In this paper, we define the generalization problem, summarize various approaches in generalization, identify the credit assignment problem, and present the problem and some solutions in measuring generalizability. We discuss anomalies in the ordering of hypotheses in a subdomain when performance is normalized and averaged, and show conditions under which anomalies can be eliminated. To generalize performance across subdomains, we present a measure called probability of win that measures the probability whether a hypothesis is better than another. Finally, we discuss some limitations in using probabilities of win and illustrate their application in finding new parameter values for TimberWolf, a package for VLSI cell placement and routing. 1 Introduction Generalization in psychology is the tendency to respond in the same way to different but similar stimuli [6]. Such transfer of tendency may be based on temporal stimuli, spatial cues, or other physical characteristics. Learning, on the...

Opponent modelling is an important issue in games programming today. Programs which do not perform opponent modelling are unlikely to take full advantage of the mistakes made by an opponent. Additionally, programs which do not adapt over time become less of a challenge to players, causing these players to lose interest. While opponent modelling can be a difficult challenge in perfect information games, where the full state of the game is known to all players at all times, it becomes an even more difficult task in games of imperfect information, where players are not always able to observe the actual state of the game. This thesis studies the problem of opponent modelling in Kuhn Poker, a small imperfect information game that contains several properties that make real-world poker games interesting. Two basic types of opponent modelling are studied, explicit modelling and implicit modelling, and their effectiveness is compared.

this document, a term name comprising a concept prefix and an integer subscript denotes a particular instance of the concept; e.g., MousePad 6 denotes a particular mouse pad and P lant 8 denotes a particular plant.