A distributed deep reinforcement learning method for traffic light control.
Bo LiuZhengtao DingPublished in: Neurocomputing (2022)
Keyphrases
- detection method
- reinforcement learning
- synthetic data
- high accuracy
- experimental evaluation
- cost function
- learning algorithm
- preprocessing
- significant improvement
- pairwise
- dynamic programming
- computational cost
- cooperative
- distributed systems
- clustering method
- evolutionary algorithm
- markov random field
- objective function
- multiscale