Offline Meta-Reinforcement Learning for Active Pantograph Control in High-Speed Railways.
Hui WangZhigang LiuGuiyang HuXufan WangZhiwei HanPublished in: IEEE Trans. Ind. Informatics (2024)
Keyphrases
- high speed
- reinforcement learning
- control problems
- optimal control
- data acquisition
- robot control
- function approximation
- real time
- low power
- control policy
- control theory
- control system
- state space
- machine learning
- action selection
- control strategies
- frame rate
- control strategy
- optimal policy
- learning algorithm
- genetic algorithm
- markov decision processes
- control method
- meta level
- adaptive control
- supervised learning
- process control
- reinforcement learning algorithms
- dynamic programming
- multi agent
- active control