Home / LLM agents & research

benstaf/FinRL_DeepSeek

LLM agents & research★ 331 GitHub starsJupyter Notebook⏱ No commits in over six months

Code for an LLM-infused risk-sensitive RL trading agent paper

What it is

The code for the paper FinRL-DeepSeek, which combines large language models with risk-sensitive reinforcement learning for trading agents. Language models process market information that then guides how the RL agent is trained and makes decisions. Researchers working where LLM agents, reinforcement learning and quantitative investing meet can reproduce and extend the study. It is paper code, so expect a research setup rather than a packaged tool.

At a glance

Research onlyOur rating, based on popularity, maintenance and how ready it is for real use.

Best for	Professional quants
Used for	Strategy research, AI agents
Markets	US equities, Multi-market
Stack	Python
Learning curve	Steep learning curve
Practical value	Medium practical value
Cost	Free and open source
Hardware	GPU optional
Maintenance	No commits in over six months