Timezone: »
Spotlight
First-Order Methods for Wasserstein Distributionally Robust MDP
Julien Grand-Clement · Christian Kroer
Markov decision processes (MDPs) are known to be sensitive to parameter specification. Distributionally robust MDPs alleviate this issue by allowing for \textit{ambiguity sets} which give a set of possible distributions over parameter sets. The goal is to find an optimal policy with respect to the worst-case parameter distribution. We propose a framework for solving Distributionally robust MDPs via first-order methods, and instantiate it for several types of Wasserstein ambiguity sets. By developing efficient proximal updates, our algorithms achieve a convergence rate of $O\left(NA^{2.5}S^{3.5}\log(S)\log(\epsilon^{-1})\epsilon^{-1.5} \right)$ for the number of kernels $N$ in the support of the nominal distribution, states $S$, and actions $A$; this rate varies slightly based on the Wasserstein setup. Our dependence on $N,A$ and $S$ is significantly better than existing methods, which have a complexity of $O\left(N^{3.5}A^{3.5}S^{4.5}\log^{2}(\epsilon^{-1}) \right)$. Numerical experiments show that our algorithm is significantly more scalable than state-of-the-art approaches across several domains.
Author Information
Julien Grand-Clement (IEOR Department, Columbia University)
Christian Kroer (Columbia University)
Related Events (a corresponding poster, oral, or spotlight)
-
2021 Poster: First-Order Methods for Wasserstein Distributionally Robust MDP »
Thu. Jul 22nd 04:00 -- 06:00 PM Room Virtual
More from the Same Authors
-
2023 Poster: Statistical Inference and A/B Testing for First-Price Pacing Equilibria »
Luofeng Liao · Christian Kroer -
2022 Poster: Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games »
Gabriele Farina · Chung-Wei Lee · Haipeng Luo · Christian Kroer -
2022 Poster: Online Learning with Knapsacks: the Best of Both Worlds »
Matteo Castiglioni · Andrea Celli · Christian Kroer -
2022 Spotlight: Online Learning with Knapsacks: the Best of Both Worlds »
Matteo Castiglioni · Andrea Celli · Christian Kroer -
2022 Spotlight: Kernelized Multiplicative Weights for 0/1-Polyhedral Games: Bridging the Gap Between Learning in Extensive-Form and Normal-Form Games »
Gabriele Farina · Chung-Wei Lee · Haipeng Luo · Christian Kroer -
2021 : Invited Speaker: Christian Kroer: Recent Advances in Iterative Methods for Large-Scale Game Solving »
Christian Kroer -
2020 Poster: Stochastic Regret Minimization in Extensive-Form Games »
Gabriele Farina · Christian Kroer · Tuomas Sandholm -
2019 Poster: Stable-Predictive Optimistic Counterfactual Regret Minimization »
Gabriele Farina · Christian Kroer · Noam Brown · Tuomas Sandholm -
2019 Poster: Regret Circuits: Composability of Regret Minimizers »
Gabriele Farina · Christian Kroer · Tuomas Sandholm -
2019 Oral: Stable-Predictive Optimistic Counterfactual Regret Minimization »
Gabriele Farina · Christian Kroer · Noam Brown · Tuomas Sandholm -
2019 Oral: Regret Circuits: Composability of Regret Minimizers »
Gabriele Farina · Christian Kroer · Tuomas Sandholm