Online Optimal Control of Affine Nonlinear Discrete-Time Systems With Unknown Internal Dynamics by Using Time-Based Policy Update.
Travis DierksSarangapani JagannathanPublished in: IEEE Trans. Neural Networks Learn. Syst. (2012)
Keyphrases
- optimal control
- optimal control problems
- linear quadratic
- infinite horizon
- continuous stirred tank reactor
- class of nonlinear systems
- control problems
- dynamic programming
- dynamical systems
- feedback control
- average cost
- lyapunov function
- brownian motion
- linear systems
- dynamic model
- optimal policy
- machine learning
- finite horizon
- differential equations
- policy gradient
- stochastic demand
- stochastic control
- markov decision processes
- mathematical model
- reinforcement learning