Multi-Agent Actor-Critic for Cooperative Resource Allocation in Vehicular Networks.
Nessrine HammamiKim Khoa NguyenPublished in: WMNC (2022)
Keyphrases
- resource allocation
- cooperative
- multi agent
- actor critic
- vehicular networks
- reinforcement learning
- policy gradient
- approximate dynamic programming
- temporal difference
- propagation model
- network coding
- resource management
- gradient method
- multi agent systems
- optimal control
- function approximation
- neuro fuzzy
- game theory
- routing scheme
- reinforcement learning algorithms
- single agent
- partially observable markov decision processes
- optimal resource allocation
- state space
- average reward
- learning algorithm
- autonomous agents
- intelligent agents
- policy iteration
- machine learning
- dynamic programming
- wireless networks
- combinatorial auctions
- markov decision processes
- real time
- supervised learning
- quality of service
- action selection
- model free
- multiple agents
- monte carlo