Learning to Play Chess Selectively by Acquiring Move Patterns

Finkelstein, Lev; Markovitch, Shaul

doi:10.3233/icg-1998-21204

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing studies have explored artificial learning with an emphasis on human learning techniques (see [14] for a summary), including the use of pattern based knowledge systems, such as [15], [16]. In these papers a system of patterns is used that is described as a hierarchical system, however it is used simply to define generalisation and specialisation of patterns which are represented independently, without re-use of constituent elements, and as such is not the kind of modular, re-usable hierarchy sought in this study.…”

Section: B Learning In Gamesmentioning

confidence: 99%

Formation and activation of feature hierarchies under reinforcement

Knittel

Bossomaier

2011

2011 IEEE Congress of Evolutionary Computation (CEC)

View full text Add to dashboard Cite

Representation of knowledge through a hierarchy of re-used elements, and the discovery of intermediate terms for learning, is an area of increasing interest in artificial learning. Such a hierarchy is a recognised aspect of human visual processing and has an important role in recognition of objects. A hierarchy allows efficiency of representation, and a manner of preserving links between related concepts. The use of such an approach in an artificial system requires addressing processes for discovery of features, and for activation of features according to an observation. Learning Classifier Systems provide a means of developing a population of rules relevant to a task according to reinforcement, capturing features of the problem in a population of rules. Implementation of a hierarchical representation to define rules is examined using the Activation-Reinforcement Classifier System, acting in a game environment. Two methods of activation of fragments are examined, one using a parallel activation method allowing multiple interpretations to be active in tandem, the other based on attention to a single higher level concept at once, using a limited working memory. Attention to a high level rule provides a bias on the low level features to be activated. Trials show the system operates successfully on the game of Dots and Boxes with a large game size, and is able to extract relevant features of the game using a body of 4000 autonomously produced features. The attentionbased activation method operates with a reduced memory requirement and faster processing time than the parallel method. The network of features produced shows a scale-free connectivity distribution, a common property of many human semantic networks.

show abstract

Section: B Learning In Gamesmentioning

confidence: 99%

Formation and activation of feature hierarchies under reinforcement

Knittel

Bossomaier

2011

2011 IEEE Congress of Evolutionary Computation (CEC)

View full text Add to dashboard Cite

show abstract

“…This approach is known in the game-playing community as plausible move generation or selective search. Finkelstein and Markovitch (1998) describe an approach for learning a selection strategy by acquiring move patterns. Their approach, which depends on a graph-based representation of states, is appropriate for games similar to chess but not for bridge.…”

Section: Resource-bounded Reasoningmentioning

confidence: 99%

Learning to bid in bridge

Amit

Markovitch

2006

Mach Learn

View full text Add to dashboard Cite

Bridge bidding is considered to be one of the most difficult problems for gameplaying programs. It involves four agents rather than two, including a cooperative agent. In addition, the partial observability of the game makes it impossible to predict the outcome of each action. In this paper we present a new decision-making algorithm that is capable of overcoming these problems. The algorithm allows models to be used for both opponent agents and partners, while utilizing a novel model-based Monte Carlo sampling method to overcome the problem of hidden information. The paper also presents a learning framework that uses the above decision-making algorithm for co-training of partners. The agents refine their selection strategies during training and continuously exchange their refined strategies. The refinement is based on inductive learning applied to examples accumulated for classes of states with conflicting actions. The algorithm was empirically evaluated on a set of bridge deals. The pair of agents that co-trained significantly improved their bidding performance to a level surpassing that of the current state-of-the-art bidding algorithm.

show abstract

“…Morph is reported to be stronger than NeuroChess, but is still rather weak. Although not an RL work, the approach of Finkelstein and Markovitch (1998) is also worth mentioning. Instead of board patterns, they generate move patterns -in RL terms, we could call them state features and state-action (or state-macro) features.…”

Section: Why Is Chess Hard To Reinforcement-learn?mentioning

confidence: 99%

“…Both approaches learn the weights of patterns by TD(λ ). Finkelstein and Markovitch (1998) modify the approach to search for state-action patterns. The difference is analogous to the difference of the value functions V (x) and Q(x,a): the latter does not need lookahead for decision making.…”

Section: Automatic Feature Constructionmentioning

confidence: 99%

Reinforcement Learning in Games

Szita

2012

Adaptation, Learning, and Optimization

View full text Add to dashboard Cite

Abstract. Reinforcement learning and games have a long and mutually beneficial common history. From one side, games are rich and challenging domains for testing reinforcement learning algorithms. From the other side, in several games the best computer players use reinforcement learning. The chapter begins with a selection of games and notable reinforcement learning implementations. Without any modifications, the basic reinforcement learning algorithms are rarely sufficient for high-level gameplay, so it is essential to discuss the additional ideas, ways of inserting domain knowledge, implementation decisions that are necessary for scaling up. These are reviewed in sufficient detail to understand their potentials and their limitations. The second part of the chapter lists challenges for reinforcement learning in games, together with a review of proposed solution methods. While this listing has a game-centric viewpoint, and some of the items are specific to games (like opponent modelling), a large portion of this overview can provide insight for other kinds of applications, too. In the third part we review how reinforcement learning can be useful in game development and find its way into commercial computer games. Finally, we provide pointers for more in-depth reviews of specific games and solution approaches.

show abstract

Learning to Play Chess Selectively by Acquiring Move Patterns

Cited by 5 publications

References 0 publications

Formation and activation of feature hierarchies under reinforcement

Formation and activation of feature hierarchies under reinforcement

Learning to bid in bridge

Reinforcement Learning in Games

Contact Info

Product

Resources

About