Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression.

Yecheng Jason Ma Jason Yan Dinesh Jayaraman Osbert Bastani

Published in: NeurIPS (2022)

Keyphrases

reinforcement learning
regression model
real time
function approximation
simple linear
model free
temporal difference
support vector regression
model selection
state space
regression problems
dynamic programming
learning process
artificial neural networks
learning algorithm
machine learning
data sets