Probabilistic Bisection Converges Almost as Quickly as Stochastic Approximation.

Peter I. Frazier Shane G. Henderson Rolf Waeber

Published in: Math. Oper. Res. (2019)

Keyphrases

stochastic approximation
monte carlo
generative model
probabilistic model
optimal solution
bayesian networks
policy iteration
dynamic programming
reinforcement learning
probability distribution