scholarly journals Dynamic Algorithm Selection Using Reinforcement Learning

2006 ◽  
Author(s):  
Warren Armstrong ◽  
Peter Christen ◽  
Eric McCreath ◽  
Alistair P Rendell
Keyword(s):  
Reinforcement Learning ◽  
Algorithm Selection ◽  
Dynamic Algorithm

Dynamic algorithm selection for pareto optimal set approximation

2016 ◽  
Vol 67 (1-2) ◽  
pp. 263-282 ◽  
Author(s):  
Ingrida Steponavičė ◽  
Rob J. Hyndman ◽  
Kate Smith-Miles ◽  
Laura Villanova
Keyword(s):  
Pareto Optimal ◽  
Algorithm Selection ◽  
Dynamic Algorithm ◽  
Pareto Optimal Set ◽  
Selection For ◽  
Set Approximation ◽  
Optimal Set

scholarly journals REDO: A Reinforcement Learning-based Dynamic Routing Algorithm Selection Method for SDN

2021 ◽  
Author(s):  
Ahmed Al-Jawad ◽  
Ioan-Sorin Comsa ◽  
Purav Shah ◽  
Orhan Gemikonakli ◽  
Ramona Trestian
Keyword(s):  
Reinforcement Learning ◽  
Routing Algorithm ◽  
Dynamic Routing ◽  
Selection Method ◽  
Algorithm Selection

Dynamic algorithm selection for multi-sensor image registration

2009 ◽  
Author(s):  
Stephen DelMarco ◽  
Victor Tom ◽  
Helen Webb ◽  
David Lefebvre
Keyword(s):  
Image Registration ◽  
Algorithm Selection ◽  
Dynamic Algorithm ◽  
Selection For

scholarly journals Adaptive Real-Time Offloading Decision-Making for Mobile Edges: Deep Reinforcement Learning Framework and Simulation Results

2020 ◽  
Vol 10 (5) ◽  
pp. 1663 ◽  
Author(s):  
Soohyun Park ◽  
Dohyun Kwon ◽  
Joongheon Kim ◽  
Youn Kyu Lee ◽  
Sungrae Cho
Keyword(s):  
Reinforcement Learning ◽  
Real Time ◽  
Data Transmission ◽  
Energy Efficient ◽  
Computing Systems ◽  
Decision Algorithm ◽  
Dynamic Algorithm ◽  
Data Intensive ◽  
Learning Framework ◽  
Task Offloading

This paper proposes a novel dynamic offloading decision method which is inspired by deep reinforcement learning (DRL). In order to realize real-time communications in mobile edge computing systems, an efficient task offloading algorithm is required. When the decision of actions (offloading enabled, i.e., computing in clouds or offloading disabled, i.e., computing in local edges) is made by the proposed DRL-based dynamic algorithm in each unit time, it is required to consider real-time/seamless data transmission and energy-efficiency in mobile edge devices. Therefore, our proposed dynamic offloading decision algorithm is designed for the joint optimization of delay and energy-efficient communications based on DRL framework. According to the performance evaluation via data-intensive simulations, this paper verifies that the proposed dynamic algorithm achieves desired performance.

The Optimal Path Finding Algorithm Based on Reinforcement Learning

2020 ◽  
Vol 12 (4) ◽  
pp. 1-18
Author(s):  
Ganesh Khekare ◽  
Pushpneel Verma ◽  
Urvashi Dhanre ◽  
Seema Raut ◽  
Shahrukh Sheikh
Keyword(s):  
Reinforcement Learning ◽  
Particle Swarm Optimization Algorithm ◽  
Positive Impact ◽  
Optimal Path ◽  
Traffic Density ◽  
Optimal Route ◽  
Swarm Optimization ◽  
Dynamic Algorithm ◽  
The World ◽  
Simulation Results

Urbanization has been extensively increased in the last decade. In proportion, the number of vehicles throughout the world is increasing broadly. The detailed survey of available optimal path algorithms is done in this article, and to ease the overall traveling process, a dynamic algorithm is proposed. The proposed algorithm takes into consideration multiple objectives like dynamic traffic density, distance, history data, etc. and provides an optimal route solution. It is hinged on reinforcement learning and capable of deciding the optimal route on its own. A comparative analysis of the proposed algorithm is done with a genetic algorithm, particle swarm optimization algorithm, and the artificial neural networks algorithm. Through simulation results, it is proved that the proposed algorithm has better efficiency, decision making, and stability. It will ease the driver's headache and make the journey more comfortable with traffic less short distance routes that will minimize overall travel time making a positive impact on traffic jams, accidents, fuel consumption, and pollution.

Sign in / Sign up

Export Citation Format

Share Document