← Search

Sreejeet Maity

2 accepted papers

2025

Adversarially-Robust TD Learning with Markovian Data: Finite-Time Rates and Fundamental Limits

AISTATS 2025poster

One of the most basic problems in reinforcement learning (RL) is policy evaluation: estimating the long-term return, i.e., value function, corresponding to a given fixed policy. The celebrated Temporal Difference (TD) learning algorithm addresses this problem, and recent work has investigated finite…

Cited by 0SourceScholar