CV

Research Interests

• Reinforcement Learning(RL), Safe Reinforcement Learning(SRL)
• Unsupervised Learning, Self-Supervised Learning(SSL)

Education

• Ph.D in Computer Science, University of Liverpool, Liverpool, England, Sep. 2023 - now
• M.S. in Computer Science, Nanjing University of Aeronautics and Astronautics, Nanjing, China, Sep. 2019 - April 2022
• B.S. in Mathematics, Nanjing University of Aeronautics and Astronautics, Nanjing, China, Sep. 2015 - June 2019

Work experience

• April 2022 - Sep. 2023: Gaming AI Researcher
  • Parametrix Technology, Shenzhen, China
  • Duties included: Appling and training RL-based Gaming AI in the most challenging gaming seconries, e.g. First-person shooter (FPS), Third-person shooter (TPS), Hero shooter (HS) games.

Publications

Greedy-Step Off-Policy Reinforcement Learning

Learning Downstream Task by Selectively Capturing Complementary Knowledge from Multiple Self-supervisedly Learning Pretexts

Highway Reinforcement Learning

Expected-Max Ensembled Q-learning with Temporally-Varying Exploration

Skills

• Skill about Machine Learning
  • Code Language: Python, C++
  • Deep Learning Framework: Torch, Tensorflow