Ontogenesis of Agency in Machines : A Multidisciplinary Review

How does agency arise in biocognitive systems? Can the emergence of agency be explained by physical laws? We review these and related questions in philosophy, psychology, biology, and physics. Based on the review we ask the questions: i) Can machines have agency? and, if so, ii) How can we build machines with agency? We examine existing work in artificial intelligence and machine learning on selfmotivated, self-teaching, and self-developing systems with respect to the ontogenesis (“coming into being”) of agency in computational systems. The impact of these “autogenic” systems or machine agency on science, technology, and humanity will be discussed.

[1]  Doina Precup,et al.  An information-theoretic approach to curiosity-driven reinforcement learning , 2012, Theory in Biosciences.

[2]  R. Swenson SPONTANEOUS ORDER, EVOLUTION, AND AUTOCATAKINETICS: THE NOMOLOGICAL BASIS FOR THE EMERGENCE OF MEANING , 1998 .

[3]  Mary A. Peterson,et al.  Cognitive Biology: Evolutionary and Developmental Perspectives on Mind, Brain, and Behavior , 2009 .

[4]  W. Prinz,et al.  Action science emerging: Introduction and leitmotifs , 2013 .

[5]  Byoung-Tak Zhang,et al.  Information-Theoretic Objective Functions for Lifelong Learning , 2013, AAAI Spring Symposium: Lifelong Machine Learning.

[6]  D. Lewkowicz,et al.  A dynamic systems approach to the development of cognition and action. , 2007, Journal of cognitive neuroscience.

[7]  Ralf Der,et al.  Predictive information and explorative behavior of autonomous robots , 2008 .

[8]  H. Sebastian Seung,et al.  Information, Prediction, and Query by Committee , 1992, NIPS.

[9]  Byoung-Tak Zhang,et al.  Self-Organizing Latent Lattice Models for Temporal Gene Expression Profiling , 2003, Machine Learning.

[10]  Jeffrey V. Nickerson,et al.  Anticipatory systems: philosophical, mathematical, and methodological foundations , 2012, Int. J. Gen. Syst..

[11]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[12]  Byoung-Tak Zhang,et al.  Cognitive learning and the multimodal memory game: Toward human-level machine learning , 2008, 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence).

[13]  L. von Bertalanffy,et al.  The theory of open systems in physics and biology. , 1950, Science.

[14]  B. Zhang Self-development learning: Constructing optimal size neural networks via in-cremental data selection , 1993 .

[15]  Estevam R. Hruschka,et al.  Toward an Architecture for Never-Ending Language Learning , 2010, AAAI.

[16]  H. Maturana,et al.  Autopoiesis and Cognition : The Realization of the Living (Boston Studies in the Philosophy of Scie , 1980 .

[17]  D. Dennett The Intentional Stance. , 1987 .

[18]  Gertrudis Van de Vijver,et al.  Evolutionary Systems Biological and Epistemological Perspectives on Selection and Self-Organization , 1998 .

[19]  M. Eigen,et al.  The Hypercycle: A principle of natural self-organization , 2009 .

[20]  Ilya Prigogine,et al.  From Being To Becoming , 1980 .

[21]  Karl J. Friston The free-energy principle: a unified brain theory? , 2010, Nature Reviews Neuroscience.

[22]  E. Schrödinger,et al.  What is life? : the physical aspect of the living cell , 1946 .

[23]  Stanley N. Salthe,et al.  Development and Evolution: Complexity and Change in Biology , 1993 .

[24]  Daniel Polani,et al.  Information Theory of Decisions and Actions , 2011 .

[25]  J. Todd,et al.  INVESTIGATIONS , 1984, The Lancet.

[26]  Michael T. Turvey,et al.  Ecological Perspective on Perception-Action: What Kind of Science Does It Entail? , 2013 .

[27]  Thomas Goschke,et al.  Volition in Action: Intentions, Control Dilemmas, and the Dynamic Regulation of Cognitive Control , 2013 .

[28]  D. Crosby Incomplete Nature: How Mind Emerged from Matter , 2011 .

[29]  Peter Stone,et al.  Empowerment for continuous agent—environment systems , 2011, Adapt. Behav..