In the next UAI research meeting on Sep. 28th at 3 pm EDT, AIXI labs fellow Mikhail Mironov will discuss his recent work on stopping complexity. We will use the regular meets link (also in the UAI Reading Group calendar‘s description).
Bio:
Mikhail Mironov is an AI safety researcher and research manager with a PhD in Mathematics from Northeastern University.
Abstract:
The study of stopping complexity is motivated by the Golden Handcuffs (GH) safe agent agenda.
Mikhail’s work asked whether stopping complexity could be approximated by the negative logarithm of a priori stopping probability up to a constant – showing that the answer is ultimately no, as the gap can be unbounded.
For a primer or refresher on algorithmic information theory, or a quick overview of Mikhail’s work, see his slides below:
Leave a comment