Metraipolis › archive › dc_80143ada39ff

Last-Iterate Convergence for Constrained MDPs: From Dual Descent to Primal-Dual — arXiv:2610.39524

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39524
License (as archived)
CC0-1.0
Archived
2026-11-01T02:25:09.275Z
SHA-256 of the archived text
2618f97de5e12e59a8ea0b2ec6fa88c8a2c0db293aa095578b268da61987d54d
Stable URL of this page
https://metraipolis.com/documento/dc_80143ada39ff

How to cite

Last-Iterate Convergence for Constrained MDPs: From Dual Descent to Primal-Dual — arXiv:2610.39524 — arXiv (en), https://arxiv.org/abs/2610.39524 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_80143ada39ff (Metraipolis archive dc_80143ada39ff, sha256 2618f97de5e12e59a8ea0b2ec6fa88c8a2c0db293aa095578b268da61987d54d)
BibTeX
@misc{dc80143ada39ff,
  title = {Last-Iterate Convergence for Constrained MDPs: From Dual Descent to Primal-Dual — arXiv:2610.39524},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39524},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_80143ada39ff; sha256 2618f97de5e12e59a8ea0b2ec6fa88c8a2c0db293aa095578b268da61987d54d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39524. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study policy optimization for infinite-horizon, discounted constrained Markov decision processes. While primal-dual ($\texttt{PD}$) methods are widely used in practice, their theoretical guarantees typically hold for an impractical mixture policy. In contrast, dual descent ($\texttt{DD}$) methods output a single policy ("last iterate") with guarantees on its performance. However, such methods require iteratively solving entropy-regularized MDPs in an inner-loop, limiting their practical effectiveness. Moreover, existing analyses rely on strong coverage assumptions that are difficult to satisfy in practice. Consequently, we first provide a new analysis of $\texttt{DD}$ methods that does not require coverage assumptions. We then employ entropy-regularized natural policy gradient and dual regularization to eliminate the inner loop, resulting in an efficient $\texttt{PD}$ algorithm. We develop a novel tracking analysis which shows that, compared to existing methods, the proposed algorithm achieves improved last-iterate convergence guarantees. Furthermore, our theoretical framework allows us to analyze a truncated bilevel method that interpolates between $\texttt{DD}$ and $\texttt{PD}$ methods. Finally, we generalize our analysis to handle linear function approximation. Compared to prior last-iterate methods, we prove stronger guarantees under less restrictive assumptions.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.39524 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:12:44.173Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).