Presentation at MODeM 2021 workshop — Soft maximin approaches to Multi-Objective Decision-making for encoding human intuitive values
By Ben Smith, Robert Klassert, and Roland Pihlakas
Presentation at Multi-Objective Decision Making workshop July 2021.
Abstract: Balancing multiple competing and conflicting objectives is an es- sential task for any artificial intelligence tasked with satisfying human values or preferences. Conflict arises both from misalign- ment between individuals with competing values, but also between conflicting value systems held by a single human. Starting with principles of loss-aversion and maximin, we designed a set of soft maximin function approaches to multi-objective decision-making. Bench-marking these functions in a set of previously-developed environments, we found that one new approach in particular, ‘split- function exp-log loss aversion’, learns faster than the thresholded alignment objective method, the state of the art described in [22]. We explore approaches to further improve multi-objective decision- making using soft maximin approaches.