Intelligent problem-solving as integrated hierarchical reinforcement learning

Although artificial reinforcement learning agents do well when rules are rigid, such as games, they fare poorly in real-world scenarios where small changes in the environment or the required actions can impair performance. The authors provide an overview of the cognitive foundations of hierarchical problem-solving, and propose steps to integrate biologically inspired hierarchical mechanisms to enable problem-solving skills in artificial agents. According to cognitive psychology and related disciplines, the development of complex problem-solving behaviour in biological agents depends on hierarchical cognitive mechanisms. Hierarchical reinforcement learning is a promising computational approach that may eventually yield comparable problem-solving behaviour in artificial agents and robots. However, so far, the problem-solving abilities of many human and non-human animals are clearly superior to those of artificial systems. Here we propose steps to integrate biologically inspired hierarchical mechanisms to enable advanced problem-solving skills in artificial agents. We first review the literature in cognitive psychology to highlight the importance of compositional abstraction and predictive processing. Then we relate the gained insights with contemporary hierarchical reinforcement learning methods. Interestingly, our results suggest that all identified cognitive mechanisms have been implemented individually in isolated computational architectures, raising the question of why there exists no single unifying architecture that integrates them. As our final contribution, we address this question by providing an integrative perspective on the computational challenges to develop such a unifying architecture. We expect our results to guide the development of more sophisticated cognitively inspired hierarchical machine learning architectures.

Automated summary

This article provides an overview of the cognitive foundations of hierarchical problem-solving and proposes steps to integrate biologically inspired hierarchical mechanisms into artificial agents. The authors highlight the promising approach of hierarchical reinforcement learning for developing problem-solving behavior in artificial agents and robots. However, the problem-solving abilities of many human and non-human animals still surpass those of artificial systems. The authors suggest integrating biologically inspired hierarchical mechanisms to improve the problem-solving skills of artificial agents.