"Offline RL Policies Should be Trained to be Adaptive."

Dibya Ghosh et al. (2022)

Details and statistics

DOI: 10.48550/arXiv.2207.02200

access: open

type: Informal or Other Publication

metadata version: 2022-07-06

a service of  Schloss Dagstuhl - Leibniz Center for Informatics