Life, uh, Finds a Way: Hyperadaptability by Behavioral Search

TL;DR

This paper introduces a theory of hyperadaptability, enabling systems to solve rare or novel problems by dynamically organizing behaviors through a self-modifying search process, demonstrated via simulations.

Contribution

It presents a new framework modeling behavior as a self-modifying search over cognitive graphs, combining Hebbian learning and harmonic neural representations for robust problem-solving.

Findings

Rapid navigation in complex mazes

High reward in challenging reinforcement learning tasks

Robust problem-solving with minimal prior experience

Abstract

Living beings are able to solve a wide variety of problems that they encounter rarely or only once. Without the benefit of extensive and repeated experience with these problems, they can solve them in an ad-hoc manner. We call this capacity to always find a solution to a physically solvable problem $hyperadaptability$. To explain how hyperadaptability can be achieved, we propose a theory that frames behavior as the physical manifestation of a self-modifying search procedure. Rather than exploring randomly, our system achieves robust problem-solving by dynamically ordering an infinite set of continuous behaviors according to simplicity and effectiveness. Behaviors are sampled from paths over cognitive graphs, their order determined by a tight behavior-execution/graph-modification feedback loop. We implement cognitive graphs using Hebbian-learning and a novel harmonic neural representation supporting flexible information storage. We validate our approach through simulation experiments showing rapid achievement of highly-robust navigation ability in complex mazes, as well as high reward on difficult extensions of classic reinforcement learning problems. This framework offers a new theoretical model for developmental learning and paves the way for robots that can autonomously master complex skills and handle exceptional circumstances.