Persuasion games are fundamental in economics and AI research and serve as the basis for important applications. However, work on this setup assumes communication with stylized messages that do not consist of rich human language. In this paper we consider a repeated sender (expert) -- receiver (decision maker) game, where the sender is fully informed about the state of the world and aims to persuade the receiver to accept a deal by sending one of several possible natural language reviews. We design an automatic expert that plays this repeated game, aiming to achieve the maximal payoff. Our expert is implemented within the Monte Carlo Tree Search (MCTS) algorithm, with deep learning models that exploit behavioral and linguistic signals in order to predict the next action of the decision maker, and the future payoff of the expert given the state of the game and a candidate review. We demonstrate the superiority of our expert over strong baselines, its adaptability to different decision makers, and that its selected reviews are nicely adapted to the proposed deal.
翻译:劝导游戏在经济学和AI研究中具有根本意义,是重要应用的基础。然而,这一设置的工作假设了与不包含丰富人文的系统化信息进行沟通。在本文件中,我们考虑的是反复发送者(专家) -- -- 接收者(决策者)游戏,发送者充分了解世界状况,目的是说服接收者接受一项交易,发送若干可能的自然语言评论之一。我们设计了一名自动专家,玩这个重复游戏,以达到最大效益。我们的专家是在蒙特卡洛树搜索算法(MCTS)中执行的,采用利用行为和语言信号的深层学习模型,以预测决策者的下一步行动,以及考虑到游戏状况和候选人审查的专家的未来报酬。我们展示了我们的专家优于强的基线、对不同决策者的适应性,其选定的审查与拟议的交易相适应。