Metraipolis › archive › dc_9a264e672571
Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence — arXiv:2609.14972
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.14972
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:11:09.946Z
- SHA-256 of the archived text
550fd4c2a074c40f81ef0d4d004dcdcee67c1572aadd69099ea913191b5d5e60- Stable URL of this page
https://metraipolis.com/documento/dc_9a264e672571
How to cite
Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence — arXiv:2609.14972 — arXiv (en), https://arxiv.org/abs/2609.14972 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9a264e672571 (Metraipolis archive dc_9a264e672571, sha256 550fd4c2a074c40f81ef0d4d004dcdcee67c1572aadd69099ea913191b5d5e60)
BibTeX
@misc{dc9a264e672571,
title = {Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and Convergence — arXiv:2609.14972},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.14972},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9a264e672571; sha256 550fd4c2a074c40f81ef0d4d004dcdcee67c1572aadd69099ea913191b5d5e60},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14972. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study continuous-time and possibly high-dimensional stochastic control problems where drift coefficients and running reward functions are unknown. Due to these missing model primitives, we take the exploratory, reinforcement learning (RL) framework of Wang, Zariphopoulou, and Zhou(2020) with relaxed controls and entropy regularization. The objective is to develop theoretically grounded, efficient and scalable RL algorithms to learn both the optimal value functions (which also solve the exploratory HJB equation) and optimal exploratory feedback control policies. When the diffusion coefficients do not contain control, we employ probabilistic representations of both the optimal value function and its gradient based on an auxiliary state process depending only on the diffusion part of the original dynamics. With a delicate analysis on some properly defined mappings and their fixed points, this leads to the introduction of our policy iteration algorithms and their convergence. We demonstrate the performance of our algorithms through various numerical examples. Finally, we study a special control-dependent diffusion case where probability representation of the Hessian is called for. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Numerical Analysis (math.NA); Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2609.14972 — 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 2026-10-15T23:54:14.726Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).