Taming the Noise in Reinforcement Learning via Soft Updates.

Roy Fox Ari Pakman Naftali Tishby

Published in: UAI (2016)

Keyphrases

reinforcement learning
noise level
noisy data
optimal policy
missing data
noise reduction
machine learning
multi agent
random noise
transfer learning
noise model
function approximation
robotic control
data sets
image noise
signal to noise ratio
learning problems
image enhancement
learning process