Yansong Li, Shuo Han. Accelerating Model-Free Policy Optimization Using Model-Based Gradient: A Composite Optimization Perspective. In Roya Firoozi, Negar Mehr, Esen Yel, Rika Antonova, Jeannette Bohg, Mac Schwager, Mykel J. Kochenderfer, editors, Learning for Dynamics and Control Conference, L4DC 2022, 23-24 June 2022, Stanford University, Stanford, CA, USA. Volume 168 of Proceedings of Machine Learning Research, pages 304-315, PMLR, 2022. [doi]
@inproceedings{LiH22-12, title = {Accelerating Model-Free Policy Optimization Using Model-Based Gradient: A Composite Optimization Perspective}, author = {Yansong Li and Shuo Han}, year = {2022}, url = {https://proceedings.mlr.press/v168/li22a.html}, researchr = {https://researchr.org/publication/LiH22-12}, cites = {0}, citedby = {0}, pages = {304-315}, booktitle = {Learning for Dynamics and Control Conference, L4DC 2022, 23-24 June 2022, Stanford University, Stanford, CA, USA}, editor = {Roya Firoozi and Negar Mehr and Esen Yel and Rika Antonova and Jeannette Bohg and Mac Schwager and Mykel J. Kochenderfer}, volume = {168}, series = {Proceedings of Machine Learning Research}, publisher = {PMLR}, }