Sets of objectives for a multi-objective RL agent to optimize — LessWrong

Ben Smith

Abstract

Background: A multi-objective decision-making AI Previously I've proposed balancing multiple objectives via multi-objective RL as a method to achieve…

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.