Exploratory Randomization for Discrete-Time Risk-Sensitive Benchmarked Investment Management with Reinforcement Learning

By Sébastien Lleo, Wolfgang Runggaldier

Published 2026-03-03

Everscope rating

1782.7

Relevance to quantitative trading

8 / 10

Implementation complexity

8 / 10

Reproducibility

2 / 5

About this paper

Methodology: Free Energy-Entropy Duality (FEED) for Risk-Sensitive Control with Exploratory Randomization. Problem types: Portfolio Optimization, Reinforcement Learning, Optimization, Risk Management, Stochastic Control, Game Theory (Zero-Sum Stochastic Games).

arXiv:2603.00738 · Paper rankings

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