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.
翻译:人-计算机互动应用中的强化学习代理(RL)要求用户在运作良好之前反复互动。为了解决这个“寒冷开始”问题,我们建议采用一种新颖的方法,在对实际用户应用之前先使用认知模型对REL代理进行预培训。在简要回顾相关的认知模型之后,我们介绍我们的一般方法,然后从我们以前和正在进行的项目中进行两个案例研究。我们希望这份立场文件能够激发RL、HCI和认知科学研究人员之间的对话,以便探索这一方法的全部潜力。