Computational Theories of Interaction and Agency

Etukansi
Philip Agre, Stanley J. Rosenschein
MIT Press, 1996 - 767 sivua

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 special double 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 and agency. 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.Artificial Intelligence series.Special Issues of Artificial Intelligence

 

Sisältö

Computational research on interaction and agency
1
Sensorimotor transformations in the worlds of frogs and robots
53
Learning to act using realtime dynamic programming
81
systems identification for perceptually challenged agents
139
A dynamical systems perspective on agentenvironment interaction
173
On information invariants in robotics
217
The stabilization of environments
305
An architecture for adaptive intelligent systems
329
Exploiting patterns of interaction to achieve reactive behavior
483
A situated view of representation and control
515
The use of dynamics in an intelligent controller for a space faring rescue robot
541
offline design
597
Instructions intentions and expectations
619
Reinforcement learning of nonMarkov decision processes
637
Proceedings of the First International
673
The Frame Problem
689

Analysis of adaptation and environment
367
The intelligent use of space
397
Indexical knowledge and robot actiona logical account
435
Book review of Artificial Life Christopher G Langton ed Artificial Life II
737
Book review of Vision Instruction and Action David Chapman
753
Tekijänoikeudet

Yleiset termit ja lausekkeet

abstract achieve action activity adaptive agent algorithm analysis animat approach architecture Artificial Intelligence assumptions autonomous behavior codesignation constraints cognitive complexity components computational configuration convergence corresponding cost decision problem defined Definition described discussed domain dynamic programming dynamical systems effects encoded environment evaluation function example execution external formal frame problem framework given goal graph immersion implementation indexical knowledge information invariants input Intell interaction Lemma limit cycle logic methods modal logic monitoring move neural object observed operations optimal policy output parameters particular path perception performance permutation possible preconditions Proceedings properties Q-Learning qualification problem reactive real-time reasoning reinforcement learning relevant RTDP schemas Section sensor sensor system sequence shortest path problems simple simulation situation situation calculus soon sust space specific stochastic strategy structure sust task temporal theory visual world view

Viitteet tähän teokseen

Kirjaluettelon tiedot

OtsikkoComputational Theories of Interaction and Agency
Artificial intelligence
Symbolic computation: Artificial intelligence
The MIT Press series in artificial intelligence
ToimittajatPhilip Agre, Stanley J. Rosenschein
Painoskuvitettu
KustantajaMIT Press, 1996
ISBN0262510901, 9780262510905
Pituus767 sivua
  
Vie sitaattiBiBTeX EndNote RefMan