Cognitive Homeostatic Agents

Amol Kelkar (kelkar.amol@gmail.com)

Abstract

Biological organisms, including humans, can be viewed as hierarchies of homeostatic systems that regulate internal variables within viable ranges. We propose that complex brains are capable of instantiating and regulating higher order cognitive homeostatic variables. Under this view, high-level cognitive processes like planning and goal-directed behavior emerge from the regulation of these variables.

Building on this perspective, we outline a framework for constructing Cognitive Homeostatic Agents - artificial agents with a hierarchy of homeostatic subsystems. The agents store and recall trajectories representing the past and simulated future states of cognitive homeostatic variables. Online learning occurs through soft memorization of new trajectories that lead to favorable states. Once a cognitive homeostatic variable representing a goal is established, behavior arises from recalling trajectories that to move the agent towards target ranges for all its homeostatic variables, including the cognitive homeostatic variables.

This framework provides a principled way to ground an agent’s hierarchical, local and distributed reward functions, enable open-ended learning, and realize high-level cognitive capabilities in an integrated architecture. It draws inspiration from emerging evidence in neuroscience while providing a roadmap to engineer sophisticated autonomous agents. Exploring this direction further may lead to fundamental insights into the nature of mind and intelligence.

Publications

• Amol Kelkar. 2021. Cognitive Homeostatic Agents: Blue Sky Ideas Track. In Proc. of the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2021), Online, May 3–7, 2021, IFAAMAS, 5 pages. [PDF]