Deep Reinforcement Learning Two-Way Transit Signal Priority Algorithm for Optimizing Headway Adherence and Speed.
Wen Xun HuHirotaka IshiharaChuhan ChenAmer ShalabyBaher AbdulhaiPublished in: IEEE Trans. Intell. Transp. Syst. (2023)
Keyphrases
- dynamic programming
- learning algorithm
- reinforcement learning
- recognition algorithm
- computational complexity
- k means
- detection algorithm
- worst case
- preprocessing
- experimental evaluation
- matching algorithm
- monte carlo
- high accuracy
- non stationary
- high speed
- signal processing
- clustering method
- computational cost
- processing speed
- least squares
- machine learning
- np hard
- cost function
- optimal solution
- state space
- simulated annealing
- significant improvement
- search space
- objective function
- times faster
- similarity measure
- genetic algorithm