paper-with-me

홈 › Papers

Structured Reinforcement Learning for Combinatorial Decision-Making

2025-05-25 · Heiko Hoppe, Léo Baty, Louis Bouvier, Axel Parmentier, Maximilian Schiffer

Reinforcement learning (RL) is increasingly applied to real-world problems involving complex and structured decisions, such as routing, scheduling, and assortment planning. These settings challenge standard RL algorithms, which struggle to scale, generalize, and exploit structure in the presence of combinatorial action spaces. We propose Structured Reinforcement Learning (SRL), a novel actor-critic framework that embeds combinatorial optimization layers into the actor neural network. We enable end-to-end learning of the actor via Fenchel-Young losses and provide a geometric interpretation of SRL as a primal-dual algorithm in the dual of the moment polytope. Across six environments with exogenous and endogenous uncertainty, SRL matches or surpasses the performance of unstructured RL and imitation learning on static tasks and improves over these baselines by up to 92% on dynamic problems, with improved stability and convergence speed.

📄 PDF Abstract BibTeX arXiv:2505.19053

Code (1)

tumbais/structured-rl 공식 구현

Tasks

Combinatorial OptimizationDecision MakingImitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Scheduling

Similar Papers 제목 키워드 기반

Learning Multi-Timescale Abstractions for Hierarchical Combinatorial Planning

2026-05-16 · Vivienne Huiling Wang, Tinghuai Wang, Joni Pajarinen arxiv

The combination of exponentially large action spaces, stochastic dynamics, and long-horizon decision-making under limited resources makes Sequential Stochastic Combinatorial Optimization (SSCO) particularly challenging f…

Hierarchical Reinforcement Learning

Reinforcement learning with combinatorial actions for coupled restless bandits

2025-03-01 · Lily Xu, Bryan Wilder, Elias B. Khalil, Milind Tambe

Reinforcement learning (RL) has increasingly been applied to solve real-world planning problems, with progress in handling large state spaces and time horizons. However, a key bottleneck in many domains is that RL method…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Sequential Decision Making

MIRACL: A Diverse Meta-Reinforcement Learning for Multi-Objective Multi-Echelon Combinatorial Supply Chain Optimisation

2026-03-05 · Rifny Rachman, Josh Tingey, Richard Allmendinger, Wei Pan 외 arxiv

Multi-objective reinforcement learning (MORL) is effective for multi-echelon combinatorial supply chain optimisation, where tasks involve high dimensionality, uncertainty, and competing objectives. However, its deploymen…

Reinforcement Learning

CORL: Reinforcement Learning of MILP Policies Solved via Branch and Bound

2025-12-11 · Akhil S Anand, Elias Aarekol, Martin Mziray Dalseg, Magnus Stalhane 외 arxiv

Combinatorial sequential decision making problems are typically modeled as mixed integer linear programs (MILPs) and solved via branch and bound (B&B) algorithms. The inherent difficulty of modeling MILPs that accurately…

Reinforcement LearningDecision Making

Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial Actions

2026-01-29 · Lingkai Kong, Anagha Satish, Hezi Jiang, Akseli Kangaslahti 외 arxiv

Reinforcement learning (RL) with combinatorial action spaces remains challenging because feasible action sets are exponentially large and governed by complex feasibility constraints, making direct policy parameterization…

Reinforcement Learning