Renewal Monte Carlo: Renewal theory based reinforcement learning.

Jayakumar Subramanian Aditya Mahajan

Published in: CoRR (2018)

Keyphrases

monte carlo
markov chain
reinforcement learning
temporal difference
stochastic approximation
state space
monte carlo simulation

monte carlo method
simulation study
policy evaluation
importance sampling
temporal difference learning
monte carlo methods
matrix inversion

monte carlo tree search
point processes
adaptive sampling
markovian decision
global illumination
optimal strategy

function approximation
markov decision processes
confidence intervals
probabilistic model
computational cost
dynamic programming