Environmental changes can profoundly impact the performance of artificial intelligence systems operating in the real world, with effects ranging from overt catastrophic failures to non-robust behaviours that do not take changing context into account. Here we argue that designing machine intelligence that can operate in open worlds, including detecting, characterizing and adapting to structurally unexpected environmental changes, is a critical goal on the path to building systems that can solve complex and relatively under-determined problems. We present and distinguish between three forms of open-world learning (OWL)—weak, semi-strong and strong—and argue that a fully developed OWL system should be antifragile, rather than merely robust. An antifragile system, an example of which is the immune system, is not only robust to adverse events, but adapts to them quickly and becomes better at handling them in subsequent encounters. We also argue that, because OWL approaches must be capable of handling the unexpected, their practical evaluation can pose an interesting conceptual problem.

环境变化可以深刻影响现实世界中运行的人工智能系统的性能，其影响范围从明显的灾难性故障到不考虑环境变化的非鲁棒行为。在这里，我们认为，设计可以在开放世界中运行的机器智能，包括检测、表征和适应结构上意想不到的环境变化，是构建能够解决复杂和相对不确定的问题的系统的关键目标。我们提出并区分了三种形式的开放世界学习（OWL）——弱、半强和强——并认为一个完全开发的 OWL 系统应该是反脆弱的，而不仅仅是鲁棒的。反脆弱系统（免疫系统就是一个例子）不仅对不良事件具有鲁棒性，而且能快速适应不良事件，并在随后的遭遇中更好地处理它们。我们还认为，由于 OWL 方法必须能够处理意外情况，因此它们的实际评估可能会提出一个有趣的概念问题。