Metraipolis › archive › dc_d7481fe4fb04

Personalized Rollout Allocation for Federated LQR Policy Optimization under Heterogeneous Process Noise — arXiv:2611.00712

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00712
License (as archived)
CC0-1.0
Archived
2026-11-03T10:19:34.891Z
SHA-256 of the archived text
65e8764a5fb77692415ddab8f9c4d350bafef986f320bf4ddf26ebd8d2301f3d
Stable URL of this page
https://metraipolis.com/documento/dc_d7481fe4fb04

How to cite

Personalized Rollout Allocation for Federated LQR Policy Optimization under Heterogeneous Process Noise — arXiv:2611.00712 — arXiv (en), https://arxiv.org/abs/2611.00712 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d7481fe4fb04 (Metraipolis archive dc_d7481fe4fb04, sha256 65e8764a5fb77692415ddab8f9c4d350bafef986f320bf4ddf26ebd8d2301f3d)
BibTeX
@misc{dcd7481fe4fb04,
  title = {Personalized Rollout Allocation for Federated LQR Policy Optimization under Heterogeneous Process Noise — arXiv:2611.00712},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00712},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d7481fe4fb04; sha256 65e8764a5fb77692415ddab8f9c4d350bafef986f320bf4ddf26ebd8d2301f3d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00712. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We study federated model-free learning of a common linear quadratic regulator (LQR) gain under a limited uplink communication budget, with clients that share dynamics and costs but experience different process-noise levels. Conventionally, clients transmit gradient matrices whose dimension equals the number of controller parameters. Exploiting the structure of two-point zeroth-order estimates, we consider an implementation in which clients transmit only one scalar cost-difference coefficient per rollout pair, while the server regenerates the associated perturbation directions from shared seeds. Communication thus scales with the number of rollout pairs rather than the controller dimension, turning the uplink budget into a rollout budget. Because noise heterogeneity produces gradient estimates of widely differing variance and every client carries equal weight in the fleet objective, uniform rollout allocation allows noisy clients to dominate the aggregated update and increases the probability of destabilizing updates. We propose a rollout-allocation scheme that assigns rollout pairs in proportion to the standard deviation of each client's estimates and show that it minimizes the variance of the aggregated update. The scheme is implemented exactly through a greedy integer allocation rule whose weights are estimated from the communicated scalars. We further prove that a single allocation factor quantifies its improvement over uniform allocation in a one-round instability bound, the certified step size, and the error floor of a joint stability and convergence guarantee. Simulations show that, under the same communication budget, personalized allocation reduces the one-step instability rate from $37\%$ to $0.3\%$.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.00712 — 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 2026-11-03T10:19:34.805Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).