Benchmarking MOEAs for solving continuous multi-objective RL problems Article Swipe

PDF

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2505.13726

Multi-objective reinforcement learning (MORL) addresses the challenge of simultaneously optimizing multiple, often conflicting, rewards, moving beyond the single-reward focus of conventional reinforcement learning (RL). This approach is essential for applications where agents must balance trade-offs between diverse goals, such as speed, energy efficiency, or stability, as a series of sequential decisions. This paper investigates the applicability and limitations of multi-objective evolutionary algorithms (MOEAs) in solving complex MORL problems. We assess whether these algorithms can effectively address the unique challenges posed by MORL and how MORL instances can serve as benchmarks to evaluate and improve MOEA performance. In particular, we propose a framework to characterize the features influencing MORL instance complexity, select representative MORL problems from the literature, and benchmark a suite of MOEAs alongside single-objective EAs using scalarized MORL formulations. Additionally, we evaluate the utility of existing multi-objective quality indicators in MORL scenarios, such as hypervolume conducting a comparison of the algorithms supported by statistical analysis. Our findings provide insights into the interplay between MORL problem characteristics and algorithmic effectiveness, highlighting opportunities for advancing both MORL research and the design of evolutionary algorithms.

Related Topics

Truth And Reconciliation Commission Of Canada

Alanis Morissette

2025 Nba Draft

28 Years Later

Reich Ministry Of Public Enlightenment And Propaganda

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2505.13726
PDF: https://arxiv.org/pdf/2505.13726
OA Status: green
OpenAlex ID: https://openalex.org/W4417298465

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4417298465

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2505.13726

Digital Object Identifier
Title: Benchmarking MOEAs for solving continuous multi-objective RL problems

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-05-19

Full publication date if available
Authors: Carlos Hernández, Roberto Santana

List of authors in order
Landing page: https://arxiv.org/abs/2505.13726

Publisher landing page
PDF URL: https://arxiv.org/pdf/2505.13726

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2505.13726

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4417298465
doi	https://doi.org/10.48550/arxiv.2505.13726
ids.doi	https://doi.org/10.48550/arxiv.2505.13726
ids.openalex	https://openalex.org/W4417298465
fwci
type	preprint
title	Benchmarking MOEAs for solving continuous multi-objective RL problems
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2505.13726
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2505.13726
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2505.13726
locations[1].id	doi:10.48550/arxiv.2505.13726
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license	cc-by
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id	https://openalex.org/licenses/cc-by
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2505.13726
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5007629410
authorships[0].author.orcid	https://orcid.org/0000-0001-7947-3684
authorships[0].author.display_name	Carlos Hernández
authorships[0].author_position	first
authorships[0].raw_author_name	Hernández, Carlos
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5034080501
authorships[1].author.orcid	https://orcid.org/0000-0002-1005-8535
authorships[1].author.display_name	Roberto Santana
authorships[1].author_position	last
authorships[1].raw_author_name	Santana, Roberto
authorships[1].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2505.13726
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Benchmarking MOEAs for solving continuous multi-objective RL problems
has_fulltext	False
is_retracted	False
updated_date	2025-12-13T14:24:00.769350
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2505.13726
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2505.13726
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2505.13726
primary_location.id	pmh:oai:arXiv.org:2505.13726
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2505.13726
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2505.13726
publication_date	2025-05-19
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	46, 100, 119, 147
abstract_inverted_index.In	96
abstract_inverted_index.We	68
abstract_inverted_index.as	39, 45, 88, 144
abstract_inverted_index.by	80, 153
abstract_inverted_index.in	63, 140
abstract_inverted_index.is	26
abstract_inverted_index.of	7, 19, 48, 58, 121, 135, 149, 180
abstract_inverted_index.or	43
abstract_inverted_index.to	90, 102
abstract_inverted_index.we	98, 131
abstract_inverted_index.EAs	125
abstract_inverted_index.Our	156
abstract_inverted_index.and	56, 82, 92, 117, 167, 177
abstract_inverted_index.can	73, 86
abstract_inverted_index.for	28, 172
abstract_inverted_index.how	83
abstract_inverted_index.the	5, 16, 54, 76, 104, 115, 133, 150, 161, 178
abstract_inverted_index.MOEA	94
abstract_inverted_index.MORL	66, 81, 84, 107, 112, 128, 141, 164, 175
abstract_inverted_index.This	24, 51
abstract_inverted_index.both	174
abstract_inverted_index.from	114
abstract_inverted_index.into	160
abstract_inverted_index.must	32
abstract_inverted_index.such	38, 143
abstract_inverted_index.(RL).	23
abstract_inverted_index.MOEAs	122
abstract_inverted_index.focus	18
abstract_inverted_index.often	11
abstract_inverted_index.paper	52
abstract_inverted_index.posed	79
abstract_inverted_index.serve	87
abstract_inverted_index.suite	120
abstract_inverted_index.these	71
abstract_inverted_index.using	126
abstract_inverted_index.where	30
abstract_inverted_index.(MORL)	3
abstract_inverted_index.agents	31
abstract_inverted_index.assess	69
abstract_inverted_index.beyond	15
abstract_inverted_index.design	179
abstract_inverted_index.energy	41
abstract_inverted_index.goals,	37
abstract_inverted_index.moving	14
abstract_inverted_index.select	110
abstract_inverted_index.series	47
abstract_inverted_index.speed,	40
abstract_inverted_index.unique	77
abstract_inverted_index.(MOEAs)	62
abstract_inverted_index.address	75
abstract_inverted_index.balance	33
abstract_inverted_index.between	35, 163
abstract_inverted_index.complex	65
abstract_inverted_index.diverse	36
abstract_inverted_index.improve	93
abstract_inverted_index.problem	165
abstract_inverted_index.propose	99
abstract_inverted_index.provide	158
abstract_inverted_index.quality	138
abstract_inverted_index.solving	64
abstract_inverted_index.utility	134
abstract_inverted_index.whether	70
abstract_inverted_index.approach	25
abstract_inverted_index.evaluate	91, 132
abstract_inverted_index.existing	136
abstract_inverted_index.features	105
abstract_inverted_index.findings	157
abstract_inverted_index.insights	159
abstract_inverted_index.instance	108
abstract_inverted_index.learning	2, 22
abstract_inverted_index.problems	113
abstract_inverted_index.research	176
abstract_inverted_index.rewards,	13
abstract_inverted_index.addresses	4
abstract_inverted_index.advancing	173
abstract_inverted_index.alongside	123
abstract_inverted_index.analysis.	155
abstract_inverted_index.benchmark	118
abstract_inverted_index.challenge	6
abstract_inverted_index.essential	27
abstract_inverted_index.framework	101
abstract_inverted_index.instances	85
abstract_inverted_index.interplay	162
abstract_inverted_index.multiple,	10
abstract_inverted_index.problems.	67
abstract_inverted_index.supported	152
abstract_inverted_index.algorithms	61, 72, 151
abstract_inverted_index.benchmarks	89
abstract_inverted_index.challenges	78
abstract_inverted_index.comparison	148
abstract_inverted_index.conducting	146
abstract_inverted_index.decisions.	50
abstract_inverted_index.indicators	139
abstract_inverted_index.optimizing	9
abstract_inverted_index.scalarized	127
abstract_inverted_index.scenarios,	142
abstract_inverted_index.sequential	49
abstract_inverted_index.stability,	44
abstract_inverted_index.trade-offs	34
abstract_inverted_index.algorithmic	168
abstract_inverted_index.algorithms.	182
abstract_inverted_index.complexity,	109
abstract_inverted_index.effectively	74
abstract_inverted_index.efficiency,	42
abstract_inverted_index.hypervolume	145
abstract_inverted_index.influencing	106
abstract_inverted_index.limitations	57
abstract_inverted_index.literature,	116
abstract_inverted_index.particular,	97
abstract_inverted_index.statistical	154
abstract_inverted_index.applications	29
abstract_inverted_index.characterize	103
abstract_inverted_index.conflicting,	12
abstract_inverted_index.conventional	20
abstract_inverted_index.evolutionary	60, 181
abstract_inverted_index.highlighting	170
abstract_inverted_index.investigates	53
abstract_inverted_index.performance.	95
abstract_inverted_index.Additionally,	130
abstract_inverted_index.applicability	55
abstract_inverted_index.formulations.	129
abstract_inverted_index.opportunities	171
abstract_inverted_index.reinforcement	1, 21
abstract_inverted_index.single-reward	17
abstract_inverted_index.effectiveness,	169
abstract_inverted_index.representative	111
abstract_inverted_index.simultaneously	8
abstract_inverted_index.Multi-objective	0
abstract_inverted_index.characteristics	166
abstract_inverted_index.multi-objective	59, 137
abstract_inverted_index.single-objective	124
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	2
citation_normalized_percentile