Dynamic Electronic Toll Collection via Multi-Agent Deep Reinforcement Learning with Edge-Based Graph Convolutional Networks.
Wei QiuHaipeng ChenBo AnPublished in: IJCAI (2019)
Keyphrases
- reinforcement learning
- multi agent
- dynamic networks
- deep learning
- cooperative
- function approximation
- dynamic environments
- state space
- single agent
- graph theory
- directed acyclic graph
- random walk
- transportation networks
- small world
- edge weights
- model free
- graph representation
- weighted graph
- average degree
- traffic signal control
- directed graph
- complex networks
- network structure
- markov decision processes
- reinforcement learning agents
- overlapping communities
- unsupervised feature learning
- graph structures
- network analysis
- graph structure
- bipartite graph
- optimal policy