Improving the Robustness of Reinforcement Learning Policies With ${\mathcal {L}_{1}}$ Adaptive Control.
Yikun ChengPan ZhaoFanxin WangDaniel J. BlockNaira HovakimyanPublished in: IEEE Robotics Autom. Lett. (2022)
Keyphrases
- adaptive control
- reinforcement learning
- optimal policy
- control problems
- nonlinear systems
- feedback control
- partially observable markov decision processes
- policy search
- function approximation
- markov decision processes
- markov decision process
- markov decision problems
- state space
- adaptive controller
- dynamic programming
- control method
- reward function
- control policy
- fitted q iteration
- chaotic systems
- model free
- autonomous control
- variable structure
- temporal difference
- reinforcement learning algorithms
- multi modal
- learning algorithm
- action space
- control law
- machine learning
- optimal control