Metraipolis › archive › dc_2fa398ef323a

Direct Knowledge Transfer for Offline Q-Learning — arXiv:2611.01942

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01942
License (as archived): CC0-1.0
Archived: 2026-11-03T11:25:13.458Z
SHA-256 of the archived text: b9246bafd31fdcd9511ede8e896651f9cc8fb0a9967ade7ff285c64224dcac52
Stable URL of this page: https://metraipolis.com/documento/dc_2fa398ef323a

How to cite

Direct Knowledge Transfer for Offline Q-Learning — arXiv:2611.01942 — arXiv (en), https://arxiv.org/abs/2611.01942 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2fa398ef323a (Metraipolis archive dc_2fa398ef323a, sha256 b9246bafd31fdcd9511ede8e896651f9cc8fb0a9967ade7ff285c64224dcac52)

BibTeX

@misc{dc2fa398ef323a,
  title = {Direct Knowledge Transfer for Offline Q-Learning — arXiv:2611.01942},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01942},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2fa398ef323a; sha256 b9246bafd31fdcd9511ede8e896651f9cc8fb0a9967ade7ff285c64224dcac52},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01942. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Data-driven sequential decision making in marketing and healthcare can benefit from observations collected in related environments, particularly when data in the environment of interest are limited. Transferring such information requires accounting for differences in rewards and transition dynamics across environments. We study knowledge transfer for offline reinforcement learning through a joint estimation framework that directly integrates source information into target value-function learning. We propose Direct Transfer Fitted Q-Iteration (DFQI), which updates the target Q-function while simultaneously borrowing the source information through an L1 penalty that links the target coefficients to a weighted aggregate of source coefficients, with both determined jointly within each Bellman update. Using sieve approximation, we establish statistical guarantees for target estimation and policy learning in stationary discounted environments with common or heterogeneous transition kernels. Empirical studies further demonstrate the effectiveness of the proposed DFQI framework in transferring source information to improve policy learning with limited target data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.01942 — 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 2026-11-03T11:02:37.839Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).