Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Michailidis, Dimitris, Röpke, Willem, Roijers, Diederik M., Ghebreab, Sennay, Santos, Fernando P.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910074248626176
author Michailidis, Dimitris
Röpke, Willem
Roijers, Diederik M.
Ghebreab, Sennay
Santos, Fernando P.
author_facet Michailidis, Dimitris
Röpke, Willem
Roijers, Diederik M.
Ghebreab, Sennay
Santos, Fernando P.
contents Multi-Objective Reinforcement Learning (MORL) aims to learn a set of policies that optimize trade-offs between multiple, often conflicting objectives. MORL is computationally more complex than single-objective RL, particularly as the number of objectives increases. Additionally, when objectives involve the preferences of agents or groups, incorporating fairness becomes both important and socially desirable. This paper introduces a principled algorithm that incorporates fairness into MORL while improving scalability to many-objective problems. We propose using Lorenz dominance to identify policies with equitable reward distributions and introduce lambda-Lorenz dominance to enable flexible fairness preferences. We release a new, large-scale real-world transport planning environment and demonstrate that our method encourages the discovery of fair policies, showing improved scalability in two large cities (Xi'an and Amsterdam). Our methods outperform common multi-objective approaches, particularly in high-dimensional objective spaces.
format Preprint
id arxiv_https___arxiv_org_abs_2411_18195
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance
Michailidis, Dimitris
Röpke, Willem
Roijers, Diederik M.
Ghebreab, Sennay
Santos, Fernando P.
Machine Learning
Multi-Objective Reinforcement Learning (MORL) aims to learn a set of policies that optimize trade-offs between multiple, often conflicting objectives. MORL is computationally more complex than single-objective RL, particularly as the number of objectives increases. Additionally, when objectives involve the preferences of agents or groups, incorporating fairness becomes both important and socially desirable. This paper introduces a principled algorithm that incorporates fairness into MORL while improving scalability to many-objective problems. We propose using Lorenz dominance to identify policies with equitable reward distributions and introduce lambda-Lorenz dominance to enable flexible fairness preferences. We release a new, large-scale real-world transport planning environment and demonstrate that our method encourages the discovery of fair policies, showing improved scalability in two large cities (Xi'an and Amsterdam). Our methods outperform common multi-objective approaches, particularly in high-dimensional objective spaces.
title Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance
topic Machine Learning
url https://arxiv.org/abs/2411.18195