Approximate Optimum Curbside Utilisation for Pick-Up and Drop-Off (PUDO) and Parking Demands Using Reinforcement Learning.
Qiming YeYuxiang FengJingshuo QiuMarc StettlerPanagiotis AngeloudisPublished in: ITSC (2022)
Keyphrases
- reinforcement learning
- policy evaluation
- function approximation
- state space
- model free
- machine learning
- robot control
- reinforcement learning algorithms
- exact solution
- dynamic programming
- least squares
- optimal policy
- global optimum
- robotic control
- temporal difference learning
- action space
- multi objective
- learning algorithm
- genetic algorithm
- piecewise linear
- control system
- multi agent
- website
- real world
- neural network