Personal Universes: A Solution to the Multi-Agent Value Alignment Problem
Artificial Intelligence
2019-01-08 v1
Abstract
AI Safety researchers attempting to align values of highly capable intelligent systems with those of humanity face a number of challenges including personal value extraction, multi-agent value merger and finally in-silico encoding. State-of-the-art research in value alignment shows difficulties in every stage in this process, but merger of incompatible preferences is a particularly difficult challenge to overcome. In this paper we assume that the value extraction problem will be solved and propose a possible way to implement an AI solution which optimally aligns with individual preferences of each user. We conclude by analyzing benefits and limitations of the proposed approach.
Cite
@article{arxiv.1901.01851,
title = {Personal Universes: A Solution to the Multi-Agent Value Alignment Problem},
author = {Roman V. Yampolskiy},
journal= {arXiv preprint arXiv:1901.01851},
year = {2019}
}