An Information Theoretic Approach to Prediction and Deliberative Decision Making of Embodied Systems

Nihat Ay and Keyan Zahedi

Contact the author: Please use for correspondence this email.
Submission date: 04. May. 2011
Pages: 7
published in: Advances in cognitive neurodynamics III : proceedings of the 3rd International Conference on Cognitive Neurodynamics 2011 ; [June 9-13, 2011, Hilton Niseko Village, Hokkaido, Japan] / Y. Yamaguchi (ed.)
Dordrecht : Springer, 2013. - P. 499 - 506
(Advances in cognitive neurodynamics) 
DOI number (of the published article): 10.1007/978-94-007-4792-0_67
Bibtex
with the following different title: Causal effects for prediction and deliberative decision making of embodied systems
Download full preprint: PDF (1967 kB)

Abstract:
This article deals with the causal structure of an agent's sensori-motor loop. Of particular interest are causal effects that can be identified from an agent-centric perspective based on in situ observations. Within this identification, the world model of the agent plays a central role. The prediction quality of an optimal world model is closely related to the notion of predictive information. Its maximization leads to interesting behavioral patterns such as coordination. This is studied in a virtual robotics scenario.