Abstract
We present preliminary results on the development of a stochastic adaptive dynamic programming theory for the data-driven, non-model-based design of robust optimal controllers for continuous-time stochastic systems. Both multiplicative noise and additive noise are considered. Two types of optimal control problems—the discounted problem and the biased problem—are investigated. Reinforcement learning and adaptive dynamic programming techniques are employed to design stochastic adaptive optimal controllers through online successive approximations of optimal solutions. Rigorous convergence proofs along with stability analysis are provided. The effectiveness of the proposed methods is validated by three illustrative practical examples arising from biological motor control and vehicle suspension control.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call