Optimizing Attention and Cognitive Control Costs Using Temporally-Layered Architectures

TL;DR

This paper introduces a biologically-inspired, temporally layered architecture for reinforcement learning that optimizes computational energy and decision costs, achieving high performance with reduced energy expenditure.

Contribution

The paper proposes a novel Temporally Layered Architecture (TLA) that manages computational costs in reinforcement learning, addressing limitations of existing algorithms in decision-bounded environments.

Findings

TLA achieves optimal performance with lower computational costs.

Existing RL algorithms struggle under decision and energy constraints.

TLA matches state-of-the-art performance while reducing compute energy use.

Abstract

The current reinforcement learning framework focuses exclusively on performance, often at the expense of efficiency. In contrast, biological control achieves remarkable performance while also optimizing computational energy expenditure and decision frequency. We propose a Decision Bounded Markov Decision Process (DB-MDP), that constrains the number of decisions and computational energy available to agents in reinforcement learning environments. Our experiments demonstrate that existing reinforcement learning algorithms struggle within this framework, leading to either failure or suboptimal performance. To address this, we introduce a biologically-inspired, Temporally Layered Architecture (TLA), enabling agents to manage computational costs through two layers with distinct time scales and energy requirements. TLA achieves optimal performance in decision-bounded environments and in continuous control environments, it matches state-of-the-art performance while utilizing a fraction of the compute cost. Compared to current reinforcement learning algorithms that solely prioritize performance, our approach significantly lowers computational energy expenditure while maintaining performance. These findings establish a benchmark and pave the way for future research on energy and time-aware control.