Metraipolis › archive › dc_8531fd4cd705

Taylor Representations for Model-Free RL in Networked MDPs — arXiv:2610.05456

Source: arXiv
Original: https://arxiv.org/abs/2610.05456
License (as archived): CC0-1.0
Archived: 2026-10-06T05:32:18.679Z
SHA-256 of the archived text: 98a60eed8fadd92af8271f8b363f2348ae1cfe2ba6dd9385e668c3edb7f48ca9
Stable URL of this page: https://metraipolis.com/documento/dc_8531fd4cd705

How to cite

Taylor Representations for Model-Free RL in Networked MDPs — arXiv:2610.05456 — arXiv, https://arxiv.org/abs/2610.05456 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8531fd4cd705 (Metraipolis archive dc_8531fd4cd705, sha256 98a60eed8fadd92af8271f8b363f2348ae1cfe2ba6dd9385e668c3edb7f48ca9)

BibTeX

@misc{dc8531fd4cd705,
  title = {Taylor Representations for Model-Free RL in Networked MDPs — arXiv:2610.05456},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05456},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8531fd4cd705; sha256 98a60eed8fadd92af8271f8b363f2348ae1cfe2ba6dd9385e668c3edb7f48ca9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05456. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In Networked Markov Decision Processes, transition dynamics are often unknown and the state--action space grows rapidly with the number of agents. In this setting, Taylor representations naturally approximate $Q$-functions, but a naive order-$n$ expansion over $N$ agents requires $\Theta(N^n)$ coefficients. We justify these expansions under smooth expected future local rewards with controlled derivatives. Under this condition, finite-speed information propagation and discounting imply that local-critic Taylor coefficients decay exponentially with the graph distance to the farthest agent involved. Discarding distant-agent coefficients and marginalizing then yield scalable local Taylor representations with a bound controlled by graph locality. Building on these representations, we propose a scalable model-free actor--critic algorithm, establishing finite-sample critic and near-stationarity guarantees for a linear LSTD critic. We then introduce a more expressive neural TD parameterization. Unlike prior constructive spectral methods, our approach covers settings without access to a known local dynamics map, such as hidden switched linear--quadratic regulation. Across three control benchmarks, our method matches or outperforms spectral baselines while scaling efficiently to large graphs.

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); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.05456 — 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 2026-10-06T05:27:06.000Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).