Online RL in Linearly qπ-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore

G. Weisz, A. György, Csaba Szepesvari
2/12/2026
DOISemantic Scholar

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Cite this paper

@article{weisz2026online,
  title  = {Online RL in Linearly qπ-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore},
  author = {G. Weisz and A. György and Csaba Szepesvari},
  year   = {2026},
  doi    = {10.48550/arXiv.2310.07811},
  url    = {https://arxiv.org/pdf/2310.07811},
  journal = {NEURIPS 2023 2023}
}

Discussion