The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Add to your list(s) Download to your calendar using vCal

• Yuting Wei (University of Pennsylvania)
• Monday 10 November 2025, 11:30-12:10
• Seminar Room 1, Newton Institute.

If you have a question about this talk, please contact nobody.

SCLW01 - Bridging Stochastic Control And Reinforcement Learning: Theories and Applications

In this talk, we investigate model robustness in reinforcement learning (RL) to reduce the sim-to-real gap in practice. We adopt the framework of distributionally robust Markov decision processes (RMDPs), aimed at learning a policy that optimizes the worst-case performance when the deployed environment falls within a prescribed uncertainty set around the nominal MDP . Despite recent efforts, the sample complexity of RMD Ps remained mostly unsettled regardless of the uncertainty set in use. It was unclear if distributional robustness bears any statistical consequences when benchmarked against standard RL. Assuming access to a generative model that draws samples based on the nominal MDP , we provide a near-optimal characterization of the sample complexity of RMD Ps when the uncertainty set is specified via either the total variation (TV) distance or χ2 divergence. The algorithm studied here is a model-based method called distributionally robust value iteration, which is shown to be near-optimal for the full range of uncertainty levels. 

This talk is part of the Isaac Newton Institute Seminar Series series.

This talk is included in these lists:

• All CMS events
• Featured lists
• INI info aggregator
• Isaac Newton Institute Seminar Series
• School of Physical Sciences
• Seminar Room 1, Newton Institute
• bld31

Note that ex-directory lists are not shown.