Optimizing Attention And Cognitive Control Costs Using Temporally-layered Architectures

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

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keypatel2023optimizing

Related papers

• Temporal Difference Models: Model-free Deep RL For Model-based Control (2018)0.00
• Learning When To Act: Interval-aware Reinforcement Learning With Predictive Temporal Structure (2026)0.00
• Control-optimized Deep Reinforcement Learning For Artificially Intelligent Autonomous Systems (2025)0.00
• Reinforcement Learning With Brain-inspired Modulation Can Improve Adaptation To Environmental Changes (2022)0.00
• RLOC: Neurobiologically Inspired Hierarchical Reinforcement Learning Algorithm For Continuous Control Of Nonlinear Dynamical Systems (2019)0.00
• When To Sense And Control? A Time-adaptive Approach For Continuous-time RL (2024)0.00
• Reducing The Deployment-time Inference Control Costs Of Deep Reinforcement Learning Agents Via An Asymmetric Architecture (2021)0.00
• Modulation Of Temporal Decision-making In A Deep Reinforcement Learning Agent Under The Dual-task Paradigm (2025)0.00