Dynamic Resource Allocation for Metaverse Applications with Deep Reinforcement Learning.
Nam H. ChuDiep N. NguyenDinh Thai HoangKhoa T. PhanEryk DutkiewiczDusit NiyatoTao ShuPublished in: WCNC (2023)
Keyphrases
- dynamic resource allocation
- reinforcement learning
- resource allocation
- function approximation
- allocation policies
- reinforcement learning algorithms
- control problems
- markov decision processes
- temporal difference learning
- learning process
- state space
- temporal difference
- direct policy search
- database
- robotic control
- semi supervised
- hidden markov models
- optimal control
- model free
- learning problems
- supervised learning
- robot control
- multi agent reinforcement learning
- relational reinforcement learning
- multi agent systems
- information systems
- machine learning
- real world