Robust Reinforcement Learning with a Stochastic Value Function.

Reiji Hatsugai Mary Inaba

Published in: MOD (2017)

Keyphrases

reinforcement learning
direct policy search
function approximators
function approximation
neural network
state space
multi agent
robust statistical
markov decision processes
learning tasks
learning problems
partial occlusion
optimal control
bayesian networks
stochastic approximation
transition model
real time