Past Member

Mengdi Wang

Affiliation
Mathematics
Field of Study
Statistical Reinforcement Learning
From 1/2020 – 7/2020:

Mengdi Wang’s research focuses on theory and algorithms for provably efficient reinforcement learning. Examples include the minimax statistical complexity for solving a Markov decision process, optimal algorithms and exploration, and dimension reduction and statistical system identification.

Dates at IAS
Member
  • Mathematics
1/20207/2020 Spring
Degrees
Massachusetts Institute of Technology Ph.D., 2013