A generalized reinforcement learning scheme for random neural networks

Lent, Ricardo

doi:10.1007/s00521-017-3223-1

Search citation statements

Order By: Relevance

Paper Sections

Select...

Edge Computing Offloading1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2024

Publication Types

Select...

Article4

Preprint1

Relationship

Self Cite0

Independent5

Authors

Journals

Cited by 7 publications

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some researchers have studied the problem of edge computing offloading based on SDN, and the main application backgrounds are task offloading and resource allocation in vehicular networks [33], computing resource sharing for IoT devices in the context of blockchain [34], and forest fire scenarios [21]. Most of the above methods are based on elaborate heuristics but ignore the lack of adaptive and intelligent handling in the face of dynamic changes in computational demand, network state and resource distribution.…”

Section: Edge Computing Offloadingmentioning

confidence: 99%

Deep reinforcement learning-based edge computing offloading algorithm for software-defined IoT

Zhu,

Zhang,

Zhang

et al. 2023

Computer Networks

View full text Add to dashboard Cite

Section: Edge Computing Offloadingmentioning

confidence: 99%

Deep reinforcement learning-based edge computing offloading algorithm for software-defined IoT

Zhu,

Zhang,

Zhang

et al. 2023

Computer Networks

View full text Add to dashboard Cite

Randomising the Simple Recurrent Network: a lightweight, energy-efficient RNN model with application to forecasting problems

Khennour,

Bouchachia,

Kherfi

et al. 2023

Neural Comput & Applic

View full text Add to dashboard Cite

Hierarchical reinforcement Thompson composition

Tanık,

Ertekin

2024

Neural Comput & Applic

View full text Add to dashboard Cite

Modern real-world control problems call for continuous control domains and robust, sample efficient and explainable control frameworks. We are presenting a framework for recursively composing control skills to solve compositional and progressively complex tasks. The framework promotes reuse of skills, and as a result quick adaptability to new tasks. The decision tree can be observed, providing insight into the agents’ behavior. Furthermore, the skills can be transferred, modified or trained independently, which can simplify reward shaping and increase training speeds considerably. This paper is concerned with efficient composition of control algorithms using reinforcement learning and soft attention. Compositional and temporal abstraction is the key to improving learning and planning in reinforcement learning. Our Thompson sampling inspired soft-attention model is demonstrated to efficiently solve the composition problem.

show abstract

A generalized reinforcement learning scheme for random neural networks

Cited by 7 publications

References 36 publications

Deep reinforcement learning-based edge computing offloading algorithm for software-defined IoT

Deep reinforcement learning-based edge computing offloading algorithm for software-defined IoT

Randomising the Simple Recurrent Network: a lightweight, energy-efficient RNN model with application to forecasting problems

Hierarchical reinforcement Thompson composition

Contact Info

Product

Resources

About