mlsanityData to 14 Oct 2026

Benchmarking MOEAs for solving continuous multi-objective RL problems

arXiv 2505.13726 ↗First posted 19 May 2025cs.NEcited by 0

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 52 references that are in the map. First posted on arXiv 19 May 2025.

Builds on

12 of 52 references.

References · 12

  1. 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
  2. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  3. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 242
  4. 2017Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learningcited by 150
  5. 2018Dynamic Weights in Multi-Objective Deep Reinforcement Learningcited by 100
  6. 2020Benchmarking in Optimization: Best Practice and Open Issuescited by 38
  7. 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 28
  8. 2018A Multi-Objective Deep Reinforcement Learning Frameworkcited by 23
  9. 2022HPO X ELA: Investigating Hyperparameter Optimization Landscapes by Means of Exploratory Landscape Analysiscited by 10
  10. 2024Near-Tight Runtime Guarantees for Many-Objective Evolutionary Algorithmscited by 5
  11. 2024MO-IOHinspector: Anytime Benchmarking of Multi-Objective Algorithms using IOHprofilercited by 2
  12. 2024Evolutionary Algorithms Are Significantly More Robust to Noise When They Ignore Itcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front
  2. 2025Variance Reduced Policy Gradient Method for Multi-Objective Reinforcement Learning
  3. 2025On Generalization Across Environments In Multi-Objective Reinforcement Learning
  4. 2025Limitations of Scalarisation in MORL: A Comparative Study in Discrete Environments
  5. 2026Momba: Network Modernization Improves Multi-Objective Reinforcement Learning
  6. 2023Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL
  7. 2024Navigating Trade-offs: Policy Summarization for Multi-Objective Reinforcement Learning
  8. 2025Multi-Objective Reinforcement Learning for Water Management