Metraipolis › archive › dc_45d0fb745e55

The Time Value of Evolution — arXiv:2608.13297

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13297
License (as archived)
CC0-1.0
Archived
2026-10-19T04:27:37.576Z
SHA-256 of the archived text
8973ecd96f63efb947c9df6224bbf953e25dc34cdfbb8bae14afb9a6eb848b46
Stable URL of this page
https://metraipolis.com/documento/dc_45d0fb745e55

How to cite

The Time Value of Evolution — arXiv:2608.13297 — arXiv (en), https://arxiv.org/abs/2608.13297 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45d0fb745e55 (Metraipolis archive dc_45d0fb745e55, sha256 8973ecd96f63efb947c9df6224bbf953e25dc34cdfbb8bae14afb9a6eb848b46)
BibTeX
@misc{dc45d0fb745e55,
  title = {The Time Value of Evolution — arXiv:2608.13297},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13297},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45d0fb745e55; sha256 8973ecd96f63efb947c9df6224bbf953e25dc34cdfbb8bae14afb9a6eb848b46},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13297. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In evolutionary search, a weak child can be a valuable ancestor that makes high-fitness regions reachable. Immediate-return control is blind to this delayed utility, penalizing mutations through their immediate offspring even when they open productive future lineages. We formalize this hidden dynamic as the time value of evolution within a finite-horizon Markov decision process. To exploit it, we introduce Lineage-Value Policy Gradients (LVPG), a long-horizon actor-critic framework for automated trading policy discovery. Our architecture decouples search control into specialized policy heads over a shared generative backbone: a bootstrapped critic head estimates the value of finite-horizon lineage potential from multi-step mutation trees, while an actor head dynamically modulates mutation intensity over the remaining search budget. We isolate the impact of long-horizon credit assignment against immediate-return optimization across 90 paired runs under matched operators, lineage supervision, folds, seeds, and budgets. Path-based credit assignment substantially accelerates finite-budget search, increasing validation best-so-far AUC by 0.394 Sharpe units. LVPG also produces fewer temporary regressions than immediate-return optimization and recovers from them more often. Finite-horizon lineage value yields more selective non-monotonic search and stronger policies within identical resource constraints.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.13297 — 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 2026-10-19T04:20:35.855Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).