マックスミン基準を用いた制約付き多目的強化学習
Constrained Multi-Objective Reinforcement Learning with Max-Min Criterion
複数の目的を公平に扱うマックスミン基準と明示的な制約充足を統合した多目的強化学習フレームワークを提案し、理論的基盤と収束解析、さらに建物熱制御や移動制御、交通管理などのシミュレーションで有効性を示した。
著者: Giseung Park, Hyunyoung Nam, Woohyeon Byeon, Amir Leshem, Youngchul Sung
分類: cs.LG
原文アブストラクト
Multi-Objective Reinforcement Learning (MORL) extends standard RL by optimizing policies with respect to multiple, often conflicting, objectives. While max-min MORL has emerged as an effective approach for promoting fairness, its applicability remains limited, particularly when constraints must be incorporated. In this paper, we propose a MORL framework that integrates the max-min criterion with explicit constraint satisfaction. We establish a theoretical foundation for the proposed framework and validate the resulting algorithm through convergence analysis and experiments in tabular settings. We further demonstrate the practical relevance of our approach in simulated building thermal control, multi-objective locomotion control, and greenhouse-gas-emission-aware traffic management. Across these domains, our method effectively balances fairness and constraint satisfaction in multi-objective decision-making.