Projected Policy Gradient Converges in a Finite Number of Iterations
Jiacai Liu, Wenye Li, and Ke Wei. Projected Policy Gradient Converges in a Finite Number of Iterations. arXiv:2311.0110, 2023.
CV
Education
Ph.D in Reinforcement Learning, Fudan University, (2023-2026)
Supervisor : Ke Wei
M.S. in Statistics, Fudan University, (2021 - 2023)
B.M. in Shanghai University of Finance and Economic, (2017 - 2021)
I rank 1st in GaoKao in Guangyuan City, Sichuan Province
Work experience
- Game AI Intern in NETEASE GAMES AI LAB, 2023.02 - 2023.07.
- Research on the sample efficiency of on-policy algorithms (such as PPO).
- Research on the Imitation Learning with GAN series algorithms.
Publications
On the Linear Convergence of Policy Gradient under Hadamard Parametrization
Jiacai Liu, Jinchi Chen, and Ke Wei. On the Linear Convergence of Policy Gradient under Hadamard Parameterization. arXiv:2305.19575, 2023.
Talks
Projected Policy Gradient Converges in a Finite Number of Iterations
Presentation at Applied Math Ph.D. Seminar, Rm1801,Guanghua East Tower
Awards
- 2023.06, IJCAI 2023 AI Olympics Competition, Champion.
- 2021.06, Chinese Collegiate Computing Competition, 1st Prize.
- 2020.06, Chinese Collegiate Computing Competition, 3rd Prize.
- 2016.03, China National High School Mathematics League, Sichuan Province, 2nd Prize.