Every parameter matters: Ensuring the convergence of federated learning with dynamic heterogeneous models reduction
H Zhou, T Lan, GP Venkataramani… - Advances in Neural …, 2024 - 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 …
clients that could potentially make unique contributions are excluded from training large …
Pre-trained large language models for industrial control
For industrial control, developing high-performance controllers with few samples and low
technical debt is appealing. Foundation models, possessing rich prior knowledge obtained …
technical debt is appealing. Foundation models, possessing rich prior knowledge obtained …
Data-driven dynamic pricing and inventory management of an omni-channel retailer in an uncertain demand environment
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 …
and consumers. In this approach, retailers often leverage their brick-and-mortar stores to …
A versatile multi-agent reinforcement learning benchmark for inventory management
Multi-agent reinforcement learning (MARL) models multiple agents that interact and learn
within a shared environment. This paradigm is applicable to various industrial scenarios …
within a shared environment. This paradigm is applicable to various industrial scenarios …
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 …
mitigating earthquake hazards. These systems strive to quickly evaluate earthquake …
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 …
field of research, approaches tend to be limited to simple, linear environments with …
[PDF][PDF] Multi-Agent Alternate Q-Learning
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 …
broad range of real applications, including logistics [10], traffic signal control [33], power …
Inertia Estimation of Nodes and System Based on ARMAX Model
Y Liu, M Sun, J Wang, B Liao… - 2024 IEEE 2nd …, 2024 - ieeexplore.ieee.org
With the integration of large-scale renewable energy units into the grid, their intrinsic low
inertia characteristics result in a decrease in the inertia level at the node hierarchy …
inertia characteristics result in a decrease in the inertia level at the node hierarchy …
Federated Deep Q-Network for Multiple Microgrids Energy Management
B Feng, G Huang, Y Chen, Z Guo, W Zhu… - 2024 IEEE 2nd …, 2024 - ieeexplore.ieee.org
The unpredictability of renewable energy sources and load fluctuations pose significant
challenges to effective microgrid energy management. Current model-based MG energy …
challenges to effective microgrid energy management. Current model-based MG energy …
Whittle Index with Multiple Actions and State Constraint for Inventory Management
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 …
problem. In this paper, we extend Whittle index to a new multi-agent reinforcement learning …