A new Q(lambda) with interim forward view and Monte Carlo equivalence.

Richard S. Sutton Ashique Rupam Mahmood Doina Precup Hado van Hasselt

Published in: ICML (2014)

Keyphrases

monte carlo
monte carlo simulation
importance sampling
monte carlo methods
markov chain
particle filter
monte carlo tree search
monte carlo method
adaptive sampling
simulation study
point processes
markovian decision
variance reduction
matrix inversion
global illumination
optimal strategy
random sampling