Learning in POMDPs is Sample-Efficient with Hindsight Observability.

Jonathan Lee Alekh Agarwal Christoph Dann Tong Zhang

Published in: ICML (2023)

Keyphrases

reinforcement learning
learning process
supervised learning
unsupervised learning
learning tasks
decision theoretic
data sets
machine learning
support vector
online learning
markov decision processes
predictive state representations