构建开放世界棋类游戏平台，测试AI应对意外新情况的能力
Generating Novelty in Open-World Multi-Agent Strategic Board Games
- 分离智能体与模拟器，避免预设新奇性导致的模型偏差
- 通过大富翁游戏演示，验证AI在未知变化中的适应性
- 适用于研究鲁棒AI和开放世界新奇应对能力的团队
我们介绍了 GNOME（开放世界多智能体环境中生成新奇性的实验平台），该平台旨在测试多智能体AI系统在面对新奇情况时的有效性。GNOME 将AI对弈智能体的开发与模拟器分离，从而允许出现未预期的新奇性（即不受模型选择偏见影响的新情况）。通过网络图形界面，该平台已在 NeurIPS 2020 上使用大富翁游戏进行演示，促进关于AI鲁棒性及现实环境中新奇本质的开放讨论。本文进一步详述了演示的关键要素，并概述了当前用于DARPA人工智能与学习科学开放世界新奇性（SAIL-ON）项目中，评估外部团队开发的新奇适应型对弈智能体的实验设计。
原文摘要 · Abstract (English)
We describe GNOME (Generating Novelty in Open-world Multi-agent Environments), an experimental platform that is designed to test the effectiveness of multi-agent AI systems when faced with \emph{novelty}. GNOME separates the development of AI gameplaying agents with the simulator, allowing \emph{unanticipated} novelty (in essence, novelty that is not subject to model-selection bias). Using a Web GUI, GNOME was recently demonstrated at NeurIPS 2020 using the game of Monopoly to foster an open discussion on AI robustness and the nature of novelty in real-world environments. In this article, we further detail the key elements of the demonstration, and also provide an overview of the experimental design that is being currently used in the DARPA Science of Artificial Intelligence and Learning for Open-World Novelty (SAIL-ON) program to evaluate external teams developing novelty-adaptive gameplaying agents.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。