mlsanityData to 14 Oct 2026

A Multi-Agent system for Multi-Objective constrained optimization

arXiv 2606.20236 ↗First posted 18 Jun 2026cs.AI cs.LG cs.MAcited by 0

Not on the map. Why?

Abstract (arXiv)

Many decision-making problems in computing and networking systems can be naturally formulated as cost-minimization problems under performance constraints. In dynamic environments, reinforcement learning (RL) is often used to solve such problems at runtime by embedding both costs and constraint violations into a single scalar reward through weighted penalty terms, following a Lagrangian-inspired formulation. However, in this context the behavior of the learned policy critically depends on the choice of these weights, which are typically selected manually. This makes it difficult to identify an appropriate trade-off between optimizing the primary objective and effectively avoiding constraint violations, particularly in non-stationary environments where their relative importance may change. This paper presents MAMO (Multi-Agent system for Multi-Objective constrained optimization), an approach to tackle this balancing problem through multi-agent RL. MAMO decouples task execution from objective design by formulating the selection of reward weights as a learning problem, providing a !rst step towards more autonomous and robust RL-based solutions for constrained optimization problems in dynamic environments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 30 references that are in the map. First posted on arXiv 18 Jun 2026.

Builds on

10 of 30 references.

References · 10

  1. 2018Human-level performance in first-person multiplayer games with population-based deep reinforcement learningcited by 264
  2. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  3. 2018Meta-Gradient Reinforcement Learningcited by 159
  4. 2020Learning to Utilize Shaping Rewards: A New Approach of Reward Shapingcited by 114
  5. 2018On Learning Intrinsic Rewards for Policy Gradient Methodscited by 102
  6. 2018Meta-Learning for Multi-objective Reinforcement Learningcited by 34
  7. 2025Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weightingcited by 23
  8. 2023Behavior Alignment via Reward Function Optimizationcited by 16
  9. 2023Survey on Lagrangian Relaxation for MILP: Importance, Challenges, Historical Review, Recent Advancements, and Opportunitiescited by 3
  10. 2024Black Box Meta-Learning Intrinsic Rewardscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Achieving Equilibrium under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning
  2. 2024Multi-Objective Optimization Using Adaptive Distributed Reinforcement Learning
  3. 2025Multi-Agent Reinforcement Learning for Resources Allocation Optimization: A Survey
  4. 2024Conflict-Averse Gradient Aggregation for Constrained Multi-Objective Reinforcement Learning
  5. 2021On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning
  6. 2025Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution
  7. 2026MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning
  8. 2024Natural Policy Gradient and Actor Critic Methods for Constrained Multi-Task Reinforcement Learning