Switching Policies based on Multi-Objective Reinforcement Learning for Adaptive Traffic Signal Control.
Takumi SaikiSachiyo AraiPublished in: SICE (2022)
Keyphrases
- traffic signal control
- multi objective
- reinforcement learning
- traffic simulator
- traffic signal
- evolutionary algorithm
- optimal policy
- particle swarm optimization
- policy search
- genetic algorithm
- objective function
- control policy
- learning algorithm
- state space
- markov decision processes
- markov decision process
- neural network
- dynamic programming
- optimal control