Dynamic Resource Allocation for Metaverse Applications with Deep Reinforcement Learning.
Nam H. ChuDiep N. NguyenDinh Thai HoangKhoa T. PhanEryk DutkiewiczDusit NiyatoTao ShuPublished in: CoRR (2023)
Keyphrases
- dynamic resource allocation
- reinforcement learning
- resource allocation
- function approximation
- state space
- allocation policies
- machine learning
- multi agent
- model free
- temporal difference
- deep learning
- dynamic programming
- robotic control
- markov decision processes
- reinforcement learning algorithms
- optimal control
- transfer learning
- temporal difference learning
- policy search
- real time
- learning problems
- optimal policy
- learning process
- decision making
- learning algorithm
- direct policy search
- radial basis function
- relational reinforcement learning
- autonomous learning
- continuous state
- control problems
- action selection
- expert systems
- neural network
- databases