SciPhy Reinforcement Learning for Portfolio Optimization

By Igor Halperin, Andrey Itkin

Published 2026-07-17

Everscope rating

1562.1

Relevance to quantitative trading

9 / 10

Implementation complexity

8 / 10

Reproducibility

3 / 5

About this paper

Methodology: SciPhyRL (Scientific Physics-Informed Reinforcement Learning). Problem types: Portfolio Optimization, Reinforcement Learning, Optimization, Risk Management, Algorithmic Execution.

arXiv:2607.15195 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.