arxivst stuff from arxiv that you should probably bookmark

Can AIs learn to avoid human interruption?

Abstract · Apr 10, 2017 14:38 ·

learners interruptions safe interruptibility agents independent sufficient notion conditions cs-ai cs-lg cs-ma stat-ml

Arxiv Abstract

  • El Mahdi El Mhamdi
  • Rachid Guerraoui
  • Hadrien Hendrikx
  • Alexandre Maurer

Recent progress in artificial intelligence enabled the design and implementation of autonomous computing devices, agents, that may interact and learn from each other to achieve certain goals. Sometimes however, a human operator needs to intervene and interrupt an agent in order to prevent certain dangerous situations. Yet, as part of their learning process, agents may link these interruptions that impact their reward to specific states, and deliberately avoid them. The situation is particularly challenging in a distributed context because agents might not only learn from their own past interruptions, but also from those of other agents. This paper defines the notion of safe interruptibility as a distributed computing problem, and studies this notion in the two main learning frameworks: joint action learners and independent learners. We give realistic sufficient conditions on the learning algorithm for safe interruptibility in the case of joint action learners, yet show that these conditions are not sufficient for independent learners. We show however that if agents can detect interruptions, it is possible to prune the observations to ensure safe interruptibility even for independent learners

Read the paper (pdf) »