Nonlinear Control of Quadcopters via Approximate Dynamic Programming.

Angel Romero Paul N. Beuchat Yvonne R. Stürz Roy S. Smith John Lygeros

Published in: ECC (2019)

Keyphrases

approximate dynamic programming
control policy
reinforcement learning
linear program
control system
dynamic programming
step size
stochastic dynamic programming
highly nonlinear
special case
feature extraction
linear programming
convergence rate
long run
factored mdps