论文标题
以民主AI为中心的以人为本的机制设计
Human-centered mechanism design with Democratic AI
论文作者
论文摘要
建立与人类价值一致的人工智能（AI）是一个未解决的问题。在这里，我们开发了一种名为“民主AI”的人类研究管道，其中使用强化学习来设计人类在大多数人中偏爱的社会机制。一大批人玩了一款在线投资游戏，其中涉及决定是保留货币捐赠还是与他人分享以取得集体利益。在两种不同的重新分配机制下，共享收入返还给玩家，一种由人工智能设计，另一种是由人类设计的。 AI发现了一种机制，该机制纠正了最初的财富失衡，批准了自由骑手并成功赢得了多数票。通过优化人类偏好，民主AI可能是一种有前途的政策创新的有前途的方法。
Building artificial intelligence (AI) that aligns with human values is an unsolved problem. Here, we developed a human-in-the-loop research pipeline called Democratic AI, in which reinforcement learning is used to design a social mechanism that humans prefer by majority. A large group of humans played an online investment game that involved deciding whether to keep a monetary endowment or to share it with others for collective benefit. Shared revenue was returned to players under two different redistribution mechanisms, one designed by the AI and the other by humans. The AI discovered a mechanism that redressed initial wealth imbalance, sanctioned free riders, and successfully won the majority vote. By optimizing for human preferences, Democratic AI may be a promising method for value-aligned policy innovation.
