Reinforcement learning vs. rule-based adaptive traffic signal control: A Fourier basis linear function approximation for traffic signal control.
Theresa ZiemkeLucas Nunes AlegreAna L. C. BazzanPublished in: AI Commun. (2021)
Keyphrases
- traffic signal control
- function approximation
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- temporal difference learning
- model free
- state space
- learning algorithm
- reinforcement learning algorithms
- markov decision processes
- radial basis function
- dynamic programming
- traffic signal
- machine learning
- learning tasks
- multi agent
- supervised learning
- transfer learning
- actor critic
- policy evaluation
- neural network
- policy gradient
- control policy
- action selection
- optimal policy