Curriculum Vitae
Also available in PDF format.
Jiajun Fan (+86) 17822018001 | jiajunf3@illinois.edu | www.jiajunfan.com Education
- M.Eng. of Computer Technology; GPA 3.97/4.0, Tsinghua University, 2021-2024 (expected)
- Service: Served as the reviewer or PC member at top-tier machine learning conferences, including ICML, and NeurIPS.
- Relevant Course: Stochastic Processes (A). Big Data Systems (A+). Digital Processing of Speech Signals (A).Data visualization (A+).
- B.Eng. of Intelligent Science and Technology; GPA 93.28/100 (3.9/4.0), Nankai University, 2017-2021
- Honors: Ranked 1st in my major and obtained the National Scholarship twice (Top 1).
- Service: Served as the minister at the Faculty Student Council.
Research Interest
- Primary: Effective reinforcement learning and its applications to transfer learning, AGI and embodied AI.
- Secondary: Interpretability of reinforcement learning and its applications to effective agent learning.
Publications
Jiajun Fan, He Ba, Xian Guo, Jianye Hao, "Critic PI2: Master Continuous Planning via Policy Improvement with Path Integrals and Deep Actor-Critic Reinforcement Learning." Arxiv, 2020.
Jiajun Fan, "A Review for Deep Reinforcement Learning in Atari: Benchmarks, Challenges, and Solutions." In the proceedings of AAAI-22 Workshop on Reinforcement Learning in Games, 2021.
Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, "An Entropy Regularization Free Mechanism for Policy-based Reinforcement Learning." Arxiv, 2021.
Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, "CASA: A Bridge Between Gradient of Policy Improvement and Policy Evaluation." Arxiv, 2021.
Jiajun Fan, Changnan Xiao, Yue Huang, "GDI: Rethinking What Makes Reinforcement Learning Different From Supervised Learning." In the proceedings of AAAI-22 Workshop on Reinforcement Learning in Games, 2021.
Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, Haiyan Yin, "CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration." In the proceedings of Deep Reinforcement Learning Workshop NeurIPS 2022, 2022.
Hao Wang, Zhichao Chen, Jiajun Fan, Yuxin Huang, Weiming Liu, Xinggao Liu, "Entire Space Counterfactual Learning: Tuning, Analytical Properties and Industrial Applications." Arxiv, 2022.
Jiajun Fan, Changnan Xiao, "Generalized Data Distribution Iteration." In the proceedings of International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, 2022.
Awards
- 2021 Outstanding Graduates, Nankai University Tianjin, China
- 2021 Excellent Graduation Thesis, Nankai University Tianjin, China
- 2021 Tang Lixin Scholarship, Nankai University Tianjin, China
- 2020 National Scholarship, Nankai University Tianjin, China
- 2020 Nomination for Zhou Enlai Scholarship, Nankai University Tianjin, China
- 2019 National Scholarship, Nankai University Tianjin, China
- 2019 3st Prize, Robocup@HOME Education World Final Sydney, Australia
- 2019 Bronze Medal, ACM / ICPC Asia Regional Contest Xuzhou, China
- 2018 National 2st Prize, National College Students Mathematical Contest in Modeling Tianjin, China
- 2018 The First Prize Scholarship, Nankai University Tianjin, China
Academic Service
- Reviewer of Thirty-seventh Annual Conference on Neural Information Processing Systems. NeurIPS 2023
- Reviewer of The Fortieth International Conference on Machine Learning. ICML 2023
- Reviewer of Thirty-sixth Conference on Neural Information Processing Systems. NeurIPS 2022
