Routing with Pickup and Delivery via Deep Reinforcement Learning.
Özge Aslan YildizInci SariçiçekKemal ÖzkanAhmet YaziciPublished in: SIU (2024)
Keyphrases
- reinforcement learning
- function approximation
- temporal difference
- routing problem
- markov decision processes
- routing algorithm
- state space
- optimal policy
- robotic control
- deep learning
- routing protocol
- ad hoc networks
- wireless ad hoc networks
- multi agent
- reinforcement learning algorithms
- shortest path
- network topology
- model free
- optimal control
- network topologies
- multi agent reinforcement learning
- ant algorithm
- dynamic programming
- learning environment
- learning problems
- transition model
- policy search
- routing decisions
- machine learning