Every parameter matters: Ensuring the convergence of federated learning with dynamic heterogeneous models reduction

H Zhou, T Lan, GP Venkataramani… - Advances in Neural …, 2023 - proceedings.neurips.cc
Abstract Cross-device Federated Learning (FL) faces significant challenges where low-end
clients that could potentially make unique contributions are excluded from training large …

Pre-trained large language models for industrial control

L Song, C Zhang, L Zhao, J Bian - ar** high-performance controllers with few samples and low
technical debt is appealing. Foundation models, possessing rich prior knowledge obtained …

A versatile multi-agent reinforcement learning benchmark for inventory management

X Yang, Z Liu, W Jiang, C Zhang, L Zhao… - arxiv preprint arxiv …, 2023 - arxiv.org
Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn
within a shared environment. This paradigm is applicable to various industrial scenarios …

Data-driven dynamic pricing and inventory management of an omni-channel retailer in an uncertain demand environment

S Liu, J Wang, R Wang, Y Zhang, Y Song… - Expert Systems with …, 2024 - Elsevier
In recent years, omni-channel retailing has become immensely popular among both retailers
and consumers. In this approach, retailers often leverage their brick-and-mortar stores to …

Seismonet: A proximal policy optimization-based earthquake early warning system using dilated convolution layers and online data augmentation

S Banar, R Mohammadi - Expert Systems with Applications, 2024 - Elsevier
Abstract In seismic safety, Earthquake Early Warning (EEW) systems are indispensable for
mitigating earthquake hazards. These systems strive to quickly evaluate earthquake …

Whittle index with multiple actions and state constraint for inventory management

C Zhang, X Wang, W Jiang, X Yang… - The twelfth …, 2024 - openreview.net
Whittle index is a heuristic tool that leads to good performance for the restless bandits
problem. In this paper, we extend Whittle index to a new multi-agent reinforcement learning …

Neural inventory control in networks via hindsight differentiable policy optimization

M Alvo, D Russo, Y Kanoria - arxiv preprint arxiv:2306.11246, 2023 - arxiv.org
We argue that inventory management presents unique opportunities for reliably applying
and evaluating deep reinforcement learning (DRL). Toward reliable application, we …

[PDF][PDF] Multi-Agent Alternate Q-Learning

K Su, S Zhou, J Jiang, C Gan, X Wang… - Proceedings of the 23rd …, 2024 - aamas.csc.liv.ac.uk
Cooperative multi-agent reinforcement learning (MARL) is a wellabstracted model for a
broad range of real applications, including logistics [10], traffic signal control [33], power …

Cooperative multi-agent reinforcement learning for inventory management

M Khirwar, KS Gurumoorthy, AA Jain… - … Conference on Machine …, 2023 - Springer
Abstract With Reinforcement Learning (RL) for inventory management (IM) being a nascent
field of research, approaches tend to be limited to simple, linear environments with …

Research on Applications of Virtual Power Plants for Power Grid Peak-shaving Under Inertia Constraints

X Jiang, Y Liu, J Wu, D Hu - 2023 13th International …, 2023 - ieeexplore.ieee.org
Large-scale influx of renewable energy into current electric power grid increases risks
regarding frequency instability and makes power grid peak-shaving knotty. The solution lies …