Jiawei Huang, Nan Jiang. On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction. In Gustau Camps-Valls, Francisco J. R. Ruiz, Isabel Valera, editors, International Conference on Artificial Intelligence and Statistics, AISTATS 2022, 28-30 March 2022, Virtual Event. Volume 151 of Proceedings of Machine Learning Research, pages 2658-2705, PMLR, 2022. [doi]
@inproceedings{HuangJ22, title = {On the Convergence Rate of Off-Policy Policy Optimization Methods with Density-Ratio Correction}, author = {Jiawei Huang and Nan Jiang}, year = {2022}, url = {https://proceedings.mlr.press/v151/huang22a.html}, researchr = {https://researchr.org/publication/HuangJ22}, cites = {0}, citedby = {0}, pages = {2658-2705}, booktitle = {International Conference on Artificial Intelligence and Statistics, AISTATS 2022, 28-30 March 2022, Virtual Event}, editor = {Gustau Camps-Valls and Francisco J. R. Ruiz and Isabel Valera}, volume = {151}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, }