Research agenda for training aligned AIs using concave utility functions following the principles of homeostasis and diminishing returns — LessWrong

Roland Pihlakas

Abstract

This conceptual overview post is intended to explain what I mean by the principles of "homeostasis", "diminishing returns", and "balancing" - how the…

Research area

agent foundationsagentic aiai values alignmentdeceptiondiminishing returnsevalsgovernancehomeostasisloss aversionmulti-objective balancingmulti-objective reinforcement learningsocio-technical accountabilityutility functionsverification
Published
—
Source
other
View paper
Sign in to read and join the discussion.