Using Cognitive Models to Train Warm Start Reinforcement Learning Agents for Human-Computer Interactions

TL;DR

This paper proposes using cognitive models to pre-train reinforcement learning agents, aiming to improve their initial performance in human-computer interaction settings and reduce the cold start problem.

Contribution

It introduces a novel methodology of integrating cognitive models into RL training, supported by case studies demonstrating its potential benefits.

Findings

Pre-training RL agents with cognitive models enhances early performance.

The approach fosters interdisciplinary collaboration between RL, HCI, and cognitive science.

Initial case studies show promising results in reducing the cold start issue.

Abstract

Reinforcement learning (RL) agents in human-computer interactions applications require repeated user interactions before they can perform well. To address this "cold start" problem, we propose a novel approach of using cognitive models to pre-train RL agents before they are applied to real users. After briefly reviewing relevant cognitive models, we present our general methodological approach, followed by two case studies from our previous and ongoing projects. We hope this position paper stimulates conversations between RL, HCI, and cognitive science researchers in order to explore the full potential of the approach.