paper-with-me

홈 › Papers

Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning

2025-10-02 · Olivier Goudet, Quentin Suire, Adrien Goëffon, Frédéric Saubion, Sylvain Lamprier arxiv

We introduce an order-invariant reinforcement learning framework for black-box combinatorial optimization. Classical estimation-of-distribution algorithms (EDAs) often rely on learning explicit variable dependency graphs, which can be costly and fail to capture complex interactions efficiently. In contrast, we parameterize a multivariate autoregressive generative model trained without a fixed variable ordering. By sampling random generation orders during training, a form of information-preserving dropout, the model is encouraged to be invariant to variable order, promoting search-space diversity, and shaping the model to focus on the most relevant variable dependencies, improving sample efficiency. We adapt Group Relative Policy Optimization (GRPO) to this setting, providing stable policy-gradient updates from scale-invariant advantages. Across a wide range of benchmark algorithms and problem instances of varying sizes, our method frequently achieves the best performance and consistently avoids catastrophic failures.

📄 PDF Abstract BibTeX arXiv:2510.01824

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

SAINT: Attention-Based Modeling of Sub-Action Dependencies in Multi-Action Policies

2025-05-17 · Matthew Landers, Taylor W. Killian, Thomas Hartvigsen, Afsaneh Doryab

The combinatorial structure of many real-world action spaces leads to exponential growth in the number of possible actions, limiting the effectiveness of conventional reinforcement learning algorithms. Recent approaches …

Combinatorial Black-Box Optimization with Expert Advice

2020-06-06 · Hamid Dadkhahi, Karthikeyan Shanmugam, Jesus Rios, Payel Das 외

We consider the problem of black-box function optimization over the boolean hypercube. Despite the vast literature on black-box function optimization over continuous domains, not much attention has been paid to learning …

Reinforcement Learning Enhanced Quantum-inspired Algorithm for Combinatorial Optimization

2020-02-11 · Dmitrii Beloborodov, A. E. Ulanov, Jakob N. Foerster, Shimon Whiteson 외

Quantum hardware and quantum-inspired algorithms are becoming increasingly popular for combinatorial optimization. However, these algorithms may require careful hyperparameter tuning for each problem instance. We use a r…

Combinatorial OptimizationHyperparameter Optimizationreinforcement-learningReinforcement Learning+2

Combinatorial Bayesian Optimization with Random Mapping Functions to Convex Polytopes

2020-11-26 · Jungtaek Kim, Seungjin Choi, Minsu Cho

Bayesian optimization is a popular method for solving the problem of global optimization of an expensive-to-evaluate black-box function. It relies on a probabilistic surrogate model of the objective function, upon which …

Bayesian Optimizationglobal-optimization

A Generative Neural Annealer for Black-Box Combinatorial Optimization

2025-05-14 · Yuan-Hang Zhang, Massimiliano Di Ventra

We propose a generative, end-to-end solver for black-box combinatorial optimization that emphasizes both sample efficiency and solution quality on NP problems. Drawing inspiration from annealing-based algorithms, we trea…

Combinatorial OptimizationData Augmentationglobal-optimization