# A Multi-Agent system for Multi-Objective constrained optimization

arXiv: https://arxiv.org/abs/2606.20236 · HTML: https://mlsanity.com/paper/2606.20236/

## 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 (most cited first, 10 of 10)

- [Human-level performance in first-person multiplayer games with population-based deep reinforcement learning](https://mlsanity.com/paper/1807.01281/) (2018)
- [A Practical Guide to Multi-Objective Reinforcement Learning and Planning](https://mlsanity.com/paper/2103.09568/) (2021)
- [Meta-Gradient Reinforcement Learning](https://mlsanity.com/paper/1805.09801/) (2018)
- [Learning to Utilize Shaping Rewards: A New Approach of Reward Shaping](https://mlsanity.com/paper/2011.02669/) (2020)
- [On Learning Intrinsic Rewards for Policy Gradient Methods](https://mlsanity.com/paper/1804.06459/) (2018)
- [Meta-Learning for Multi-objective Reinforcement Learning](https://mlsanity.com/paper/1811.03376/) (2018)
- [Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting](https://mlsanity.com/paper/2509.11452/) (2025)
- [Behavior Alignment via Reward Function Optimization](https://mlsanity.com/paper/2310.19007/) (2023)
- [Survey on Lagrangian Relaxation for MILP: Importance, Challenges, Historical Review, Recent Advancements, and Opportunities](https://mlsanity.com/paper/2301.00573/) (2023)
- [Black Box Meta-Learning Intrinsic Rewards](https://mlsanity.com/paper/2407.21546/) (2024)

## 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.