Accelerating Model-Free Policy Optimization Using Model-Based Gradient: A Composite Optimization Perspective

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},
}