Jian Shen
Quantitative Researcher
Pudong, Shanghai, China
Summary
🤩
Rockstar🎓
Top SchoolJian Shen is a quantitative researcher with a decade of experience bridging deep learning and reinforcement learning research with real-world quantitative finance applications at Tianyan Capital in Shanghai. He holds a PhD in Computer Science from Shanghai Jiao Tong University and has hands-on expertise implementing and improving core RL algorithms—DQN variants, DDPG and REINFORCE—demonstrated through substantive contributions to an open-source Hands-on-RL repository. Comfortable moving models from research to production, he specializes in enhancing algorithm stability and performance for both discrete and continuous control tasks. Based in Pudong, Jian combines rigorous academic training with practical engineering discipline, often focusing on subtle algorithmic tweaks that yield measurable improvements in trading- and decision-making systems.
10 years of coding experience
Doctor's Degree, Computer Science, Doctor's Degree, Computer Science at Shanghai Jiao Tong University
Github Skills (10)
dqn10
machine-learning10
pytorch10
python10
reinforcement-learning10
ddpg10
deep-learning9
gymnasium9
openai-gym9
algorithms9
Programming languages (2)
Github contributions (5)
boyu-ai/Hands-on-RL
Aug 2021 - Nov 2022
https://hrl.boyuai.com/
Role in this project:
ML Engineer
ML EngineerContributions:13 commits, 12 pushes, 1 branch in 1 year 3 months
Contributions summary:Jian's commits primarily focus on implementing and improving Deep Q-Network (DQN) algorithms for reinforcement learning. They've integrated Double DQN and Dueling DQN, showcasing expertise in enhancing DQN performance. Furthermore, the user has developed and implemented DDPG (Deep Deterministic Policy Gradient) algorithm for continuous control tasks, signifying a strong understanding of policy-based reinforcement learning. The contributions also include code for the REINFORCE algorithm, further solidifying their experience in policy gradient methods and practical application within the reinforcement learning domain.
reinforcement-learninggymnasiumdeep-reinforcement-learningq-learning
RockySJ/WDGRL
Nov 2017 - Feb 2018
Contributions:16 commits, 13 pushes, 1 branch in 3 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.