"RL with KL penalties is better viewed as Bayesian inference."

Tomasz Korbak, Ethan Perez, Christopher L. Buckley (2022)

Details and statistics

DOI: 10.48550/ARXIV.2205.11275

access: open

type: Informal or Other Publication

metadata version: 2022-05-30

a service of  Schloss Dagstuhl - Leibniz Center for Informatics