Synthesizing Control Barrier Functions With Feasible Region Iteration for Safe Reinforcement Learning.
Yujie YangYuhang ZhangWenjun ZouJianyu ChenYuming YinShengbo Eben LiPublished in: IEEE Trans. Autom. Control. (2024)
Keyphrases
- reinforcement learning
- control problems
- robot control
- optimal control
- control method
- function approximation
- control policy
- control system
- optimal policy
- mobile robot
- action selection
- learning algorithm
- machine learning
- markov decision processes
- input image
- hidden markov models
- learning classifier systems
- model free
- adaptive control
- control theory