Abstract. We consider Reinforcement Learning for average reward zerosum stochastic games. We present and analyze two algorithms. The first is based on relative Q-learning and the ...
Abstract: Group-oriented web information systems (GWISs) are web-based dataintensive systems that are used by a group of people in order to fulfill common tasks. In particular, th...
Klaus-Dieter Schewe, Bernhard Thalheim, Roland Kas...
Abstract. A temporal logic is proposed as a tool for specifying properties of Klaim programs. Klaim is an experimental programming language that supports a programming paradigm whe...
This paper proposes an evolutionary framework where a network service is created from a group of autonomous agents that interact and evolve. Agents in our framework are capable of ...
Developing a learner model containing an accurate representation of a learner’s knowledge is made more difficult in distributed learning environments where the learner uses mult...
Christopher A. Brooks, Mike Winter, Jim E. Greer, ...