An application of convex optimization concepts to approximate dynamic programming.

Edilson F. Arruda Marcelo D. Fragoso João Bosco Ribeiro do Val

Published in: ACC (2008)

Keyphrases

convex optimization
approximate dynamic programming
linear program
convex relaxation
interior point methods
reinforcement learning
convex optimization problems
total variation
dynamic programming
step size
primal dual
image processing
operator splitting
higher order
particle swarm optimization
norm minimization