Adaptation to criticality through organizational invariance in embodied agents

I just published with Manuel Bedia a paper in Scientific Reports that results from an exploration of how tools from statistical mechanics could be used to model adaptive mechanisms. In this paper, we explore how adaptation to criticality could be used as a general adaptive mechanism in robots controlled by a neural network, using a simple mechanism that preserves a specific structure of correlations. This has interesting implications for thinking about neural and cognitive systems, which instead of relying on internal representations about an external world could adapt by preserving a complex structure of internal correlations.

Aguilera, M & Bedia, MG (2018). Adaptation to criticality through organizational invariance in embodied agents. Scientific Reports volume 8, Article number: 7723 (2018). doi:10.1038/s41598-018-25925-4


Abstract: Many biological and cognitive systems do not operate deep within one or other regime of activity. Instead, they are poised at critical points located at phase transitions in their parameter space. The pervasiveness of criticality suggests that there may be general principles inducing this behaviour, yet there is no well-founded theory for understanding how criticality is generated at a wide span of levels and contexts. In order to explore how criticality might emerge from general adaptive mechanisms, we propose a simple learning rule that maintains an internal organizational structure from a specific family of systems at criticality. We implement the mechanism in artificial embodied agents controlled by a neural network maintaining a correlation structure randomly sampled from an Ising model at critical temperature. Agents are evaluated in two classical reinforcement learning scenarios: the Mountain Car and the Acrobot double pendulum. In both cases the neural controller appears to reach a point of criticality, which coincides with a transition point between two regimes of the agent’s behaviour. These results suggest that adaptation to criticality could be used as a general adaptive mechanism in some circumstances, providing an alternative explanation for the pervasive presence of criticality in biological and cognitive systems.



About maguilera0

Miguel Aguilera is a Postdoctoral Research Fellow at the IAS Research Center for Life, Mind and Society at the University of the Basque Country. He has been a visiting researcher at the Cognitive Science Program at Indiana University and the Ikegami Lab in the Department of General Systems Studies at the University of Tokyo, and a postdoctoral fellow at the University of the University of Zaragoza and the University of the Balearic Islands. His research focuses on autonomy in biological and social systems from an interdisciplinary perspective, integrating insights from cognitive science, theoretical neuroscience, computational modeling, adaptive behaviour, and complex systems. It combines nonlinear and dynamical models, evolutionary algorithms, and mathematical analysis from dynamical systems, network and information theory, to generate and understand situated and embodied models of agency in the realms of artificial life and evolutionary robotics, computational neuroscience, collective intelligence practices and socio-technical systems.
This entry was posted in Adaptive Behavior, Uncategorized and tagged , , . Bookmark the permalink.