Divide and Conquer: Provably Unveiling the Pareto Front with Multi-Objective Reinforcement Learning
On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization
Abstract (arXiv)
An important challenge in multi-objective reinforcement learning is obtaining a Pareto front of policies to attain optimal performance under different preferences. We introduce Iterated Pareto Referent Optimisation (IPRO), which decomposes finding the Pareto front into a sequence of constrained single-objective problems. This enables us to guarantee convergence while providing an upper bound on the distance to undiscovered Pareto optimal solutions at each step. We evaluate IPRO using utility-based metrics and its hypervolume and find that it matches or outperforms methods that require additional assumptions. By leveraging problem-specific single-objective solvers, our approach also holds promise for applications beyond multi-objective reinforcement learning, such as planning and pathfinding.
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. First posted on arXiv 11 Feb 2024.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front
- 2026Post Hoc Extraction of Pareto Fronts for Continuous Control
- 2024Traversing Pareto Optimal Policies: Provably Efficient Multi-Objective Reinforcement Learning
- 2024Toward Finding Strong Pareto Optimal Policies in Multi-Agent Reinforcement Learning
- 2025An exploration for higher efficiency in multi objective optimisation with reinforcement learning
- 2026Deterministic Pareto-Optimal Policy Synthesis for Multi-Objective Reinforcement Learning
- 2024Pareto Inverse Reinforcement Learning for Diverse Expert Policy Generation
- 2026PA2D-MORL: Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement Learning