Metraipolis › archive › dc_1a6d136e4e7f

Reinforcement learning to choose optimizers — arXiv:2609.01811

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01811
License (as archived)
CC0-1.0
Archived
2026-10-17T05:01:05.896Z
SHA-256 of the archived text
062eea9ee69c20c77364c4f6e722aac86465e3b5be50fe3e012c8cffa0eaef1b
Stable URL of this page
https://metraipolis.com/documento/dc_1a6d136e4e7f

How to cite

Reinforcement learning to choose optimizers — arXiv:2609.01811 — arXiv (en), https://arxiv.org/abs/2609.01811 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1a6d136e4e7f (Metraipolis archive dc_1a6d136e4e7f, sha256 062eea9ee69c20c77364c4f6e722aac86465e3b5be50fe3e012c8cffa0eaef1b)
BibTeX
@misc{dc1a6d136e4e7f,
  title = {Reinforcement learning to choose optimizers — arXiv:2609.01811},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01811},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1a6d136e4e7f; sha256 062eea9ee69c20c77364c4f6e722aac86465e3b5be50fe3e012c8cffa0eaef1b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01811. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

No single optimization method is uniformly best for all problems, and the most suitable optimizer choice can change during a run. Existing approaches that change optimizer during execution typically predetermine part of the strategy: the portfolio is restricted to one algorithm class, the switch occurs once at a fixed time, or the frequency of decisions is treated as a hyperparameter rather than a learned one. We introduce "Reinforcement Learning to Choose Optimizers", which formulates the optimization algorithm choice as a sequential decision-making problem. At each decision, a recurrent policy reads the current run state and decides both which optimizer should be used next and for how long. The portfolio includes both gradient-based and derivative-free optimizers, and each switch passes on the current best solution and a representative step size. A context proxy conditions a gating network over expert heads, and training employs a decoupled actor-critic whose return is expressed in the same empirical runtime distribution metric used at evaluation. Training tasks and portfolio are designed jointly so that no optimizer dominates. On unseen problems, the learned policy outperforms every portfolio optimizer at all but the smallest budgets, and it remains robust under distribution shift.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.LG).
Categorie arXiv: Neural and Evolutionary Computing (cs.NE) ; Machine Learning (cs.LG); Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2609.01811 — 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 2026-10-17T04:09:43.353Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).