Planning to Avoid Side Effects

In sequential decision making, objective specifications are often underspecified or incomplete, neglecting to take into account potential (negative) side effects. Executing plans without consideration of their side effects can lead to catastrophic outcomes – a concern recently raised in relation to the safety of AI. In this paper we investigate how to avoid side effects in a symbolic planning setting. We study the notion of minimizing side effects in the context of a planning environment where multiple independent agents co-exist. We define (classes of) negative side effects in terms of their effect on the agency of those other agents. Finally, we show how plans which minimize side effects of different types can be computed via compilations to cost-optimizing symbolic planning, and investigate experimentally.

Authors

• Toryn Q. Klassen
• Sheila A. McIlraith University of Toronto Vector Institute for Artificial Intelligence,
• Christian Muise Queen's University Vector Institute for Artificial Intelligence,
• Jarvis Xu

Keywords

No keywords are indexed for this paper.