paper-with-me

홈 › Papers

Reinforcement Learning for Flexibility Design Problems

2021-01-02 · Yehua Wei, Lei Zhang, Ruiyi Zhang, Shijing Si, Hao Zhang, Lawrence Carin

Flexibility design problems are a class of problems that appear in strategic decision-making across industries, where the objective is to design a ($e.g.$, manufacturing) network that affords flexibility and adaptivity. The underlying combinatorial nature and stochastic objectives make flexibility design problems challenging for standard optimization methods. In this paper, we develop a reinforcement learning (RL) framework for flexibility design problems. Specifically, we carefully design mechanisms with noisy exploration and variance reduction to ensure empirical success and show the unique advantage of RL in terms of fast-adaptation. Empirical results show that the RL-based method consistently finds better solutions compared to classical heuristics.

📄 PDF Abstract BibTeX arXiv:2101.00355

Code (0)

등록된 구현이 없습니다.

Tasks

Decision Makingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

RLOR: A Flexible Framework of Deep Reinforcement Learning for Operation Research

2023-03-23 · Ching Pui Wan, Tung Li, Jason Min Wang

Reinforcement learning has been applied in operation research and has shown promise in solving large combinatorial optimization problems. However, existing works focus on developing neural network architectures for certa…

Combinatorial OptimizationDeep Reinforcement Learningreinforcement-learningReinforcement Learning

Distributed flexibility as a cost-effective alternative to grid reinforcement

2021-09-15 · Jordan Holweger, Christophe Ballif, Nicolas Wyrsch

The deployment of distributed photovoltaics (PV) in low-voltage networks may cause technical issues such as voltage rises, line ampacity violations, and transformer overloading for distribution system operators (DSOs). T…

Differentiable Quantum Architecture Search for Quantum Reinforcement Learning

2023-09-19 · Yize Sun, Yunpu Ma, Volker Tresp

Differentiable quantum architecture search (DQAS) is a gradient-based framework to design quantum circuits automatically in the NISQ era. It was motivated by such as low fidelity of quantum hardware, low flexibility of c…

Q-LearningQuantum Machine Learningreinforcement-learningReinforcement Learning

Graph Reinforcement Learning for Network Control via Bi-Level Optimization

2023-05-16 · Daniele Gammelli, James Harrison, Kaidi Yang, Marco Pavone 외

Optimization problems over dynamic networks have been extensively studied and widely used in the past decades to formulate numerous real-world problems. However, (1) traditional optimization-based approaches do not scale…

reinforcement-learningReinforcement Learning

Open Problems and Modern Solutions for Deep Reinforcement Learning

2023-02-05 · Weiqin Chen

Deep Reinforcement Learning (DRL) has achieved great success in solving complicated decision-making problems. Despite the successes, DRL is frequently criticized for many reasons, e.g., data inefficient, inflexible and i…

Decision MakingDeep Reinforcement Learningreinforcement-learningReinforcement Learning+1