FinRL: Financial Reinforcement Learning, by Keyi Wang & Yanglet (Xiao-Yang) Liu, Columbia U.

​Check YouTube Channel for the video:

​https://www.youtube.com/channel/UCImPUcSoFqP9TcItLYOAo-A

​Abstract: 

​Financial reinforcement learning (FinRL) is an interdisciplinary field that applies reinforcement learning algorithms to financial tasks. It is now a practical paradigm for financial engineering. In this presentation, we introduce the FinRL library that enables individuals to develop their own stock trading strategies. With modular architecture and reproducible tutorials, FinRL allows users to streamline their own development of trading agents. To benchmark progress and foster community engagement, we organized a series of FinRL Contests from 2023 to 2025, covering a diverse range of financial tasks such as stock trading, crypto trading, and the use of large language model (LLM)-engineered signals. These contests attracted 230+ participants from 100+ institutions in 20+ countries. To encourage participation, we provided starter kits that feature GPU-optimized parallel market environments, ensemble learning methods, and comprehensive instructions. These contests guide our follow-up FinRL contests and also provide a reference pipeline for FinAI contests alike.

​https://github.com/AI4Finance-Foundation/FinRL

​Bio

​Keyi Wang, Master's at Northwestern University, Bachelor's at Columbia University. Research Assistant at SecureFinAI Lab at Columbia University. Organizer of FinAI Contest 2025 at IEEE CSCloud, FinRL Contest 2025 at IEEE IDS, FinRL Contest 2024 and FinRL Contest 2023 at ACM ICAIF conferences, and Regulations Challenge at COLING 2025. Reviewer of ACM ICAIF conferences. Interested in machine learning and financial engineering. 

​Xiao-Yang Liu, Ph.D., Director of SecureFinAI Lab, Columbia University. His research interests include deep reinforcement learning, big data, and high-performance computing. He created several open-source projects, such as FinRL, ElegantRL, and FinGPT. He contributed chapters to a textbook on reinforcement learning for cyber-physical systems and a textbook on tensors for data processing. He serves as a PC member for NeurIPS, ICML, ICLR, AAAI, IJCAI, AISTATS, and ICAIF. He also served as a Session Chair for IJCAI 2019. He organized Financial Challenges in Large Language Models (FinLLM)@IJCAI 2024, FinRL Competition at ACM ICAIF 2023, the First/Second Workshop on Quantum Tensor Networks in Machine Learning (QTNML) at NeurIPS 2020/2021, IJCAI 2020 Workshop on Tensor Networks Representations in Machine Learning, and the NeurIPS 2019 Workshop on Machine Learning for Autonomous Driving.

​Organized by DeAI Institute

​https://www.linkedin.com/groups/10180003/

​Co-hosts:

​​EZ.Encoder Academy

​​https://www.ez-encoder.com/

​TAPNET (Toronto AI Practitioners Network)

​​https://www.linkedin.com/company/toronto-tapnet/

​​Toronto LLM Meetup Group

​​https://lu.ma/user/usr-O5UaG1q5BbTSon2

​​By registering to attend the event, you agree to be recorded during the event.