Internal state predictability as an evolutionary precursor of self-awareness and agency

What is the evolutionary value of self-awareness and agency in intelligent agents? One way to make this problem tractable is to think about the necessary conditions that lay the foundation for the emergence of agency, and assess their evolutionary origin.We postulate that one such requirement is the predictability of the internal state trajectory. A distinct property of onepsilas own actions compared to someone elsepsilas is that onepsilas own is highly predictable, and this gives the sense of ldquoauthorshiprdquo. In order to investigate if internal state predictability has any evolutionary value, we evolved sensorimotor control agents driven by a recurrent neural network in a 2D pole-balancing task. The hidden layer activity of the network was viewed as the internal state of an agent, and the predictability of its trajectory was measured. We took agents exhibiting equal levels of performance during evolutionary trials, and grouped them into those with high or low internal state predictability (ISP). The high-ISP group showed better performance than the low-ISP group in novel tasks with substantially harder initial conditions. These results indicate that regularity or predictability of neural activity in internal dynamics of agents can have a positive impact on fitness, and, in turn, can help us better understand the evolutionary role of self-awareness and agency.

[1]  Neil Davey,et al.  Time Series Prediction and Neural Networks , 2001, J. Intell. Robotic Syst..

[2]  T. Feinberg,et al.  Where in the brain is the self? , 2005, Consciousness and Cognition.

[3]  Risto Miikkulainen,et al.  Robust non-linear control through neuroevolution , 2003 .

[4]  Carina Curto,et al.  From spikes to space: reconstructing features of the environment from spikes alone , 2007, BMC Neuroscience.

[5]  Bram Bakker,et al.  The Epsilon State Count , 2000 .

[6]  Brian Scassellati,et al.  Theory of Mind for a Humanoid Robot , 2002, Auton. Robots.

[7]  Juyang Weng,et al.  Dav: a humanoid robot platform for autonomous mental development , 2002, Proceedings 2nd International Conference on Development and Learning. ICDL 2002.

[8]  Yoonsuck Choe,et al.  Enhanced Facilitatory Neuronal Dynamics for Delay Compensation , 2007, 2007 International Joint Conference on Neural Networks.

[9]  James L. McClelland,et al.  Autonomous Mental Development by Robots and Animals , 2001, Science.

[10]  Stefan Schaal,et al.  Forward models in visuomotor control. , 2002, Journal of neurophysiology.

[11]  John G. Taylor,et al.  CODAM: A neural network model of consciousness , 2007, Neural Networks.

[12]  C.W. Anderson,et al.  Learning to control an inverted pendulum using neural networks , 1989, IEEE Control Systems Magazine.

[13]  Yoonsuck Choe,et al.  Facilitating neural dynamics for delay compensation and prediction in evolutionary neural networks , 2006, GECCO.

[14]  Risto Miikkulainen,et al.  2-D Pole Balancing with Recurrent Evolutionary Networks , 1998 .

[15]  Risto Miikkulainen,et al.  Active Guidance for a Finless Rocket Using Neuroevolution , 2003, GECCO.

[16]  Hod Lipson,et al.  Resilient Machines Through Continuous Self-Modeling , 2006, Science.

[17]  D. Wolpert,et al.  Internal models in the cerebellum , 1998, Trends in Cognitive Sciences.

[18]  Marc Joliot,et al.  Content and context in temporal thalamocortical binding , 1994 .

[19]  Kazuhiko Kawamura,et al.  Development of a robot with a sense of self , 2005, 2005 International Symposium on Computational Intelligence in Robotics and Automation.

[20]  Jeffrey L. Elman,et al.  Learning and Evolution in Neural Networks , 1994, Adapt. Behav..

[21]  Edmund T. Rolls,et al.  2007 Special Issue: A computational neuroscience approach to consciousness , 2007 .

[22]  B. Scassellati,et al.  A Bayesian Robot That Distinguishes "Self" from "Other" , 2007 .

[23]  N. Block.  On a confusion about a function of consciousness , 1995, Behavioral and Brain Sciences.

[24]  Christophe Menant.  Proposal for an Approach to Artificial Consciousness Based on Self-Consciousness , 2007, AAAI Fall Symposium: AI and Consciousness.