LGFeb 28, 2025

Reward Dimension Reduction for Scalable Multi-Objective Reinforcement Learning

arXiv:2502.20957v1h-index: 3ICLR
Originality Incremental advance
AI Analysis

This addresses scalability issues for researchers and practitioners in multi-objective reinforcement learning, though it appears incremental as it builds on dimension reduction techniques.

The paper tackles scalability challenges in multi-objective reinforcement learning by introducing a reward dimension reduction method, demonstrating significant performance improvements over existing methods in environments with up to sixteen objectives.

In this paper, we introduce a simple yet effective reward dimension reduction method to tackle the scalability challenges of multi-objective reinforcement learning algorithms. While most existing approaches focus on optimizing two to four objectives, their abilities to scale to environments with more objectives remain uncertain. Our method uses a dimension reduction approach to enhance learning efficiency and policy performance in multi-objective settings. While most traditional dimension reduction methods are designed for static datasets, our approach is tailored for online learning and preserves Pareto-optimality after transformation. We propose a new training and evaluation framework for reward dimension reduction in multi-objective reinforcement learning and demonstrate the superiority of our method in environments including one with sixteen objectives, significantly outperforming existing online dimension reduction methods.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes