Sharan Vaswani

A functional mirror ascent view of policy gradient methods with function approximation.

2021 · arXiv (Cornell University)

We use functional mirror ascent to propose a general framework (referred to as FMA-PG) for designing policy gradient methods. The functional perspective distinguishes between a policy's functional representation (what are its sufficient statistics) and its …

Near-Optimal Sample Complexity Bounds for Constrained MDPs

2022 · arXiv (Cornell University)

In contrast to the advances in characterizing the sample complexity for solving Markov decision processes (MDPs), the optimal statistical complexity for solving constrained MDPs (CMDPs) remains unknown. We resolve this question by providing minimax upper …