Provably sample-efficient RL with side information about latent dynamics.

Yao Liu Dipendra Misra Miro Dudík Robert E. Schapire

Published in: NeurIPS (2022)

Keyphrases

domain knowledge
structural information
reinforcement learning
expert systems
information sources
semantic information
function approximation
learning algorithm
query processing
information extraction
user interaction
information processing
contextual information
information sharing