Using Cognitive Models to Train Warm Start Reinforcement Learning Agents for Human-Computer Interactions
This is an incremental position paper that addresses the cold start issue for RL agents in HCI applications, potentially benefiting researchers and practitioners in RL, HCI, and cognitive science.
The paper tackles the cold start problem in reinforcement learning agents for human-computer interactions by proposing to use cognitive models for pre-training, aiming to reduce the need for repeated user interactions, though no concrete results or numbers are provided.
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.