Pré-Publication, Document De Travail Année : 2025

FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents

Résumé

This paper presents a novel risk-sensitive trading agent combining reinforcement learning and large language models (LLMs). We extend the Conditional Value-at-Risk Proximal Policy Optimization (CPPO) algorithm, by adding risk assessment and trading recommendation signals generated by a LLM from financial news. Our approach is backtested on the Nasdaq-100 index benchmark, using financial news data from the FNSPID dataset and the DeepSeek V3, Qwen 2.5 and Llama 3.3 language models. The code, data, and trading agents are available at: \url{https://github.com/benstaf/FinRL_DeepSeek}
Fichier principal
Vignette du fichier
main4.pdf (980) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04934770 , version 1 (10-02-2025)

Identifiants

Citer

Mostapha Benhenda. FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents. 2025. ⟨hal-04934770⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More