论文标题
RMM：对话框导航的递归心理模型
RMM: A Recursive Mental Model for Dialog Navigation
论文作者
论文摘要
语言指导的机器人必须能够提出人类问题并理解答案。现有的工作仅关注后者。在本文中，我们超越了遵循的指导，并介绍了一项两项代理任务，其中一个代理会导航并提出第二个指导代理人回答的问题。受到心理理论的启发，我们提出了递归心理模型（RMM）。导航代理对指导代理进行建模，以模拟给定候选者生成的问题的答案。导航代理依次模拟导航代理，以模拟生成答案所需的导航步骤。我们将进度代理人用作目标作为强化学习奖励信号，不仅要直接告知导航行动，而且还既问问题和回答。我们证明RMM可以更好地概括新的环境。对话者建模可能是人类代理对话的前进道路，机器人需要提出和回答问题。
Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers. Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. The guiding agent in turn models the navigating agent to simulate navigation steps it would take to generate answers. We use the progress agents make towards the goal as a reinforcement learning reward signal to directly inform not only navigation actions, but also both question and answer generation. We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent dialogue where robots need to both ask and answer questions.
