A proximal gradient method for control problems with non-smooth and non-convex control cost.

Carolin Natemeyer Daniel Wachsmuth

Published in: Comput. Optim. Appl. (2021)

Keyphrases

control problems
gradient method
optimal control
convex formulation
reinforcement learning
adaptive control
stochastic control
convergence rate
optimization methods
convex optimization
step size
control method
negative matrix factorization
optimal solution
machine learning
text mining
state space
control law