otherAdded by a member
A brief review of the reasons multi-objective RL could be important in AI Safety Research — LessWrong
Ben Smith
Abstract
By Ben Smith, Roland Pihlakas, and Robert Klassert …
Research area
agent foundationsagentic aiai values alignmentdeceptiondiminishing returnsevalsgovernancehomeostasisloss aversionmulti-objective balancingmulti-objective reinforcement learningsocio-technical accountabilityutility functionsverification
Published
—
Source
other
Sign in to read and join the discussion.