mlsanityData to 14 Oct 2026

Momba: Network Modernization Improves Multi-Objective Reinforcement Learning

arXiv 2608.07180 ↗First posted 7 Aug 2026cs.LG cs.AIcited by 0

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

Abstract (arXiv)

Recent advances in deep reinforcement learning (RL) have shown that improving neural network architectures can yield substantial gains in sample efficiency and asymptotic performance without altering the underlying algorithms. In contrast, work on multi-objective reinforcement learning (MORL), which aims to discover a set of policies that balance trade-offs among conflicting objectives, has predominantly focused on algorithmic innovations, leaving the area of architectures underexplored. While the optimal policies and value functions can differ significantly depending on the trade-offs, MORL algorithms commonly represent them with simple feedforward networks conditioned on the trade-off. This raises the question of whether the performance of the algorithms could be improved with more expressive function approximators. In this paper, we integrate recent advances in neural network design: (i) observation and feature normalization, (ii) weight normalization, and (iii) modeling of distributional returns with an entropy-regularized MORL algorithm. The empirical results across standard continuous control benchmarks demonstrate that these changes substantially improve the quality of the produced solution sets without requiring major changes to the underlying algorithm.

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 25 of its 43 references that are in the map. First posted on arXiv 7 Aug 2026.

Builds on

25 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Scalable Multi-Objective Reinforcement Learning with Fairness Guarantees using Lorenz Dominance27 Nov

Other references · 24

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2021Deep Reinforcement Learning at the Edge of the Statistical Precipicecited by 807
  3. 2017A Distributional Perspective on Reinforcement Learningcited by 765
  4. 2017Molecular De Novo Design through Deep Reinforcement Learningcited by 267
  5. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  6. 2022The Primacy Bias in Deep Reinforcement Learningcited by 247
  7. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 242
  8. 2018Optimization of Molecules via Deep Reinforcement Learningcited by 200
  9. 2019A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptationcited by 177
  10. 2021Dropout Q-Functions for Doubly Efficient Reinforcement Learningcited by 114
  11. 2024Bigger, Regularized, Optimistic: scaling for compute and sample-efficient continuous controlcited by 108
  12. 2018Dynamic Weights in Multi-Objective Deep Reinforcement Learningcited by 100
12 more
  1. 2020Normalization Techniques in Training DNNs: Methodology, Analysis and Applicationcited by 90
  2. 2024SimBa: Simplicity Bias for Scaling Up Parameters in Deep Reinforcement Learningcited by 76
  3. 2018Composable Deep Reinforcement Learning for Robotic Manipulationcited by 72
  4. 2022PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithmcited by 58
  5. 2023Sample-Efficient Multi-Objective Learning via Generalized Policy Improvement Prioritizationcited by 48
  6. 2023Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RLcited by 36
  7. 2021Distributional Reinforcement Learning for Multi-Dimensional Reward Functionscited by 22
  8. 2025Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalizationcited by 19
  9. 2024Foundations of Multivariate Distributional Reinforcement Learningcited by 17
  10. 2025XQC: Well-conditioned Optimization Accelerates Deep Reinforcement Learningcited by 17
  11. 2025Towards Improving Reward Design in RL: A Reward Alignment Metric for RL Practitionerscited by 10
  12. 2024Learning Pareto Set for Multi-Objective Continuous Robot Controlcited by 8

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2021On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning
  2. 2025Variance Reduced Policy Gradient Method for Multi-Objective Reinforcement Learning
  3. 2024In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning
  4. 2024C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front
  5. 2025Benchmarking MOEAs for solving continuous multi-objective RL problems
  6. 2024Navigating Trade-offs: Policy Summarization for Multi-Objective Reinforcement Learning
  7. 2025On Generalization Across Environments In Multi-Objective Reinforcement Learning
  8. 2025Limitations of Scalarisation in MORL: A Comparative Study in Discrete Environments