Over time the field of artificial intelligence has developed an "agent perspective" expanding its focus from thought to action, from search spaces to physical environments, and from problem-solving to long-term activity. Originally published as a specialdouble volume of the journal Artificial Intelligence, this book brings together fundamental work by the top researchers in artificial intelligence, neural networks, computer science, robotics, and cognitive science on the themes of interaction andagency. It identifies recurring themes and outlines a methodology of the concept of "agency." The seventeen contributions cover the construction of principled characterizations of interactions between agents and their environments, as well as the use of these characterizations to guide analysis of existing agents and the synthesis of artificial agents.
Contents: Computational Research on Interaction and Agency. Sensorimotor Transformation in the Worlds of Frogs and Robots. Learning to Act Using Real-Time Dynamic Programming. Learning Dynamics: System Identification for Perceptually Challenged Agents. A Dynamical Systems Perspctive on Agent-Environment Interaction. On Information Invariants in Robots. The Stabilization of Environments. An Architecturefor Adaptive Intelligent Systems. Analysis of Adaptation and Environment. The Intelligent Use of Space. Indexical Knowledge and Robot Action: A Logical Account. Exploiting Patterns of Interaction to Achieve Reactive Behavior. A Situated View of Representation and Control. The Use of Dynamics in an Intelligent Controller for a Space Faring Rescue Robot. On Social Laws for Artificial Agent Societies: Off-Line Design. Instructions, Intentions, and Expectations. Reinforcement Learning in Non-Markov Environments. Artificial Intelligence series. Special Issues of Artificial Intelligence Это и многое другое вы найдете в книге Computational Theories of Interaction and Agency (Artificial Intelligence) (Philip E. Agre, Stanley J. Rosenschein)