• [2021-04-22] Zeroth order methods using adaptive smoothing parameters. The first doctoral and postdoctoral forum of Shenzhen Research Institute of Big Data. (Best Paper Oral Presentation Award)

  • [2020-10-24] Efficient exploration by novelty pursuit. DAI 2020, online. [slides]

Paper Reading

My paper reading presentation at the following seminars: RL Group at CUHKSZ, Deep Learning Group at CUHKSZ and Prof. Tom Luo's Group Meeting.

  • [2021-06-11] On the linear convergence of policy gradient methods for finite MDPs. [slides]

  • [2021-04-15] Margin maximum and implicit bias. Deep Learning Group at CUHKSZ. [slides]

  • [2021-04-09] Policy gradient methods. RL Group at CUHKSZ. [slides]

  • [2021-03-09] Implicit bias of gradient descend on separable data. RL Group at CUHKSZ. [slides]

  • [2021-01-14] Model-based reinforcement learning is minimax optimal. RL Group at CUHKSZ. [slides]

  • [2020-11-28] Zeroth-order convex optimization: an introduction. Group Meeting. [slides]

  • [2020-10-08] Sample complexity of reinforcement learning with a generative oracle. RL Group at CUHKSZ. [slides]