Many real-world problems (e.g., resource management, autonomous driving, drug discovery) require optimizing multiple, conflicting objectives. Multi-objective reinforcement learning (MORL) extends classic reinforcement learning to handle multiple objectives simultaneously, yielding a set of policies that capture various trade-offs. However, the MORL field lacks complex, realistic environments and benchmarks. We introduce a water resource (Nile river basin) management case study and model it as a MORL environment. We then benchmark existing MORL algorithms on this task. Our results show that specialized water management methods outperform state-of-the-art MORL approaches, underscoring the scalability challenges MORL algorithms face in real-world scenarios.
@article{arxiv.2505.01094,
title = {Multi-Objective Reinforcement Learning for Water Management},
author = {Zuzanna Osika and Roxana Rădulescu and Jazmin Zatarain Salazar and Frans Oliehoek and Pradeep K. Murukannaiah},
journal= {arXiv preprint arXiv:2505.01094},
year = {2025}
}