A Cognitive Framework for Autonomous Agents: Toward Human-Inspired Design

TL;DR

This paper proposes a human-inspired reinforcement learning architecture that combines Pavlovian and instrumental processes, leading to faster adaptation and improved decision-making in autonomous agents navigating complex environments.

Contribution

It introduces a novel cue-guided RL framework integrating Pavlovian associations with instrumental learning, inspired by human decision-making mechanisms.

Findings

Cue-driven agents adapt faster than traditional methods.

The architecture improves navigation efficiency in unknown environments.

Agents exhibit more cooperative behavior with the new framework.

Abstract

This work introduces a human-inspired reinforcement learning (RL) architecture that integrates Pavlovian and instrumental processes to enhance decision-making in autonomous systems. While existing engineering solutions rely almost exclusively on instrumental learning, neuroscience shows that humans use Pavlovian associations to leverage predictive cues to bias behavior before outcomes occur. We translate this dual-system mechanism into a cue-guided RL framework in which radio-frequency (RF) stimuli act as conditioned (Pavlovian) cues that modulate action selection. The proposed architecture combines Pavlovian values with instrumental policy optimization, improving navigation efficiency and cooperative behavior in unknown, partially observable environments. Simulation results demonstrate that cue-driven agents adapt faster, achieving superior performance compared to traditional instrumental-solo agents. This work highlights the potential of human learning principles to reshape digital agents intelligence.