Improving Social Welfare While Preserving Autonomy via a Pareto Mediator

TL;DR

This paper introduces a Pareto Mediator that enhances social welfare in decision-making scenarios involving agents with conflicting interests, while preserving individual autonomy and demonstrating robustness to model inaccuracies.

Contribution

The paper proposes a novel Pareto Mediator approach that improves social outcomes without harming individual agents, addressing limitations of existing delegation strategies.

Findings

Significantly increases social welfare in various game settings

Performance degrades gracefully with incorrect utility models

Preserves agent autonomy through voluntary mediation

Abstract

Machine learning algorithms often make decisions on behalf of agents with varied and sometimes conflicting interests. In domains where agents can choose to take their own action or delegate their action to a central mediator, an open question is how mediators should take actions on behalf of delegating agents. The main existing approach uses delegating agents to punish non-delegating agents in an attempt to get all agents to delegate, which tends to be costly for all. We introduce a Pareto Mediator which aims to improve outcomes for delegating agents without making any of them worse off. Our experiments in random normal form games, a restaurant recommendation game, and a reinforcement learning sequential social dilemma show that the Pareto Mediator greatly increases social welfare. Also, even when the Pareto Mediator is based on an incorrect model of agent utility, performance gracefully degrades to the pre-intervention level, due to the individual autonomy preserved by the voluntary mediator.