Newest papers

When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game

Siu Tung Wong, Carlo Campajola · 2026 · arXiv

DOI: 10.48550/arXiv.2610.03598 · open-access PDF

Russian

Усиление обучения (RL) все чаще используется для финансовых проблем оптимального контроля, когда сложная динамика затрудняет получение аналитических стратегий. Существуют финансовые математические литературы, которые предоставляют много решенных моделей, чьи уравнения и контроли могут оценивать и направлять обучение; мы спрашиваем, может ли RL использовать эти результаты. Мы размещаем агента proximal policy optimization (PPO) в аналитически решенной непрерывной брокер-трейдерской игре.

Machine translation (Meta M2M100); the English original follows.

Abstract

Reinforcement learning (RL) is increasingly used for financial optimal-control problems when complex dynamics make analytical strategies difficult to obtain. There are financial mathematics literactures which provides many solved models whose equations and controls could evaluate and guide learning; we ask whether RL can exploit these results. We place a proximal policy optimisation (PPO) agent in an analytically solved continuous-time broker--trader game. PPO replaces the broker and chooses its trading speed while interacting with an informed trader and stochastic uninformed order flow. We de

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.03598, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange