V2V Routing in VANET Based on Heuristic Q-Learning.
Xiaoying YangWanli ZhangHongmei LuLiang ZhaoPublished in: Int. J. Comput. Commun. Control (2020)
Keyphrases
- reinforcement learning
- vehicular ad hoc networks
- routing protocol
- multi agent
- dynamic programming
- function approximation
- learning algorithm
- state space
- optimal solution
- network topology
- action selection
- routing problem
- search algorithm
- routing algorithm
- combinatorial optimization
- cooperative
- tabu search
- solution quality
- learning rate
- stochastic approximation
- markov decision processes
- model free
- mobile ad hoc networks
- reinforcement learning algorithms
- genetic algorithm