Multi-Objective Reinforcement Learning for Water Management

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-ofthe-art MORL approaches, underscoring the scalability challenges MORL algorithms face in real-world scenarios.

Authors

• Zuzanna Osika Delft University of Technology
• Roxana Rădulescu Utrecht University
• Jazmin Zatarain-Salazar Delft University of Technology
• Frans A. Oliehoek Delft University of Technology
• Pradeep K. Murukannaiah Technische Universiteit Delft

Keywords

• Multi-Objective Reinforcement Learning
• Water Management