Using Cognitive Models To Train Warm Start Reinforcement Learning Agents For Human-computer Interactions

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2021using

Related papers

• Userrl: Training Interactive User-centric Agent Via Reinforcement Learning (2025)0.00
• Effective Warm Start For The Online Actor-critic Reinforcement Learning Based Mhealth Intervention (2017)0.00
• Improving Multimodal Interactive Agents With Reinforcement Learning From Human Feedback (2022)0.00
• Assessing Human Interaction In Virtual Reality With Continually Learning Prediction Agents Based On Reinforcement Learning Algorithms: A Pilot Study (2021)0.00
• Human AI Interaction Loop Training: New Approach For Interactive Reinforcement Learning (2020)0.00
• Humans Are Not Boltzmann Distributions: Challenges And Opportunities For Modelling Human Feedback And Interaction In Reinforcement Learning (2022)0.00
• Human-level Reinforcement Learning Through Theory-based Modeling, Exploration, And Planning (2021)0.00
• Computerrl: Scaling End-to-end Online Reinforcement Learning For Computer Use Agents (2025)0.00