POPO: Pessimistic Offline Policy Optimization

Autor: Qiang He, Xinwen Hou, Yu Liu
Rok vydání: 2022
Zdroj: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
DOI: 10.1109/icassp43922.2022.9747886
Databáze: OpenAIRE