Zihao Deng, Siddartha Devic, Brendan Juba. Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions. 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 11280-11304, PMLR, 2022. [doi]
@inproceedings{DengDJ22, title = {Polynomial Time Reinforcement Learning in Factored State MDPs with Linear Value Functions}, author = {Zihao Deng and Siddartha Devic and Brendan Juba}, year = {2022}, url = {https://proceedings.mlr.press/v151/deng22c.html}, researchr = {https://researchr.org/publication/DengDJ22}, cites = {0}, citedby = {0}, pages = {11280-11304}, 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}, }