Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions

Gellért Weisz, Philip Amortila, Csaba Szepesvári. Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. In Vitaly Feldman, Katrina Ligett, Sivan Sabato, editors, Algorithmic Learning Theory, 16-19 March 2021, Virtual Conference, Worldwide. Volume 132 of Proceedings of Machine Learning Research, pages 1237-1264, PMLR, 2021. [doi]

@inproceedings{WeiszAS21,
  title = {Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions},
  author = {Gellért Weisz and Philip Amortila and Csaba Szepesvári},
  year = {2021},
  url = {http://proceedings.mlr.press/v132/weisz21a.html},
  researchr = {https://researchr.org/publication/WeiszAS21},
  cites = {0},
  citedby = {0},
  pages = {1237-1264},
  booktitle = {Algorithmic Learning Theory, 16-19 March 2021, Virtual Conference, Worldwide},
  editor = {Vitaly Feldman and Katrina Ligett and Sivan Sabato},
  volume = {132},
  series = {Proceedings of Machine Learning Research},
  publisher = {PMLR},
}