Representation Learning for Online and Offline RL in Low-rank MDPs.

Masatoshi Uehara Xuezhou Zhang Wen Sun

Published in: ICLR (2022)

Keyphrases

reinforcement learning
low rank
learning process
learning algorithm
markov decision processes
supervised learning
optimal policy
trace norm
neural network
state space
singular value decomposition
learning tasks
learning problems
matrix factorization
function approximation
multi task