Gellért Weisz, Csaba Szepesvári, András György 0001. TensorPlan and the Few Actions Lower Bound for Planning in MDPs under Linear Realizability of Optimal Value Functions. In Sanjoy Dasgupta, Nika Haghtalab, editors, International Conference on Algorithmic Learning Theory, 29-1 April 2022, Paris, France. Volume 167 of Proceedings of Machine Learning Research, pages 1097-1137, PMLR, 2022. [doi]
Abstract is missing.