Skip to yearly menu bar Skip to main content

Workshop: Workshop on Machine Learning Safety

Epistemic Side Effects & Avoiding Them (Sometimes)

Toryn Klassen · Parand Alizadeh Alamdari · Sheila McIlraith


AI safety research has investigated the problem of negative side effects -- undesirable changes made by AI systems in pursuit of an underspecified objective. However, the focus has been on physical side effects, such as a robot breaking a vase while moving. In this paper we introduce the notion of epistemic side effects, unintended changes made to the knowledge or beliefs of agents, and describe a way to avoid negative epistemic side effects in reinforcement learning, in some cases.

Chat is not available.