Integrating Conventional Headway Control with Reinforcement Learning to Avoid Bus Bunching.
Xiheng WangPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- control system
- control strategy
- robot control
- machine learning
- function approximation
- process control
- control strategies
- robotic control
- temporal difference
- action selection
- autonomous robots
- markov decision processes
- state space
- evaluation function
- data acquisition
- learning process
- case study
- control policy
- learning algorithm