# Robust Markov Decision Processes without Model Estimation

arXiv: https://arxiv.org/abs/2302.01248 · HTML: https://mlsanity.com/paper/2302.01248/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 2 Feb 2023.

## Builds on (most cited first, 25 of 25)

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Convex Optimization: Algorithms and Complexity](https://mlsanity.com/paper/1405.4980/) (2014)
- [Certifying Some Distributional Robustness with Principled Adversarial Training](https://mlsanity.com/paper/1710.10571/) (2017)
- [Learning Models with Uniform Performance via Distributionally Robust Optimization](https://mlsanity.com/paper/1810.08750/) (2018)
- [Variance-based regularization with convex objectives](https://mlsanity.com/paper/1610.02581/) (2016)
- [Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model](https://mlsanity.com/paper/2005.12900/) (2020)
- [Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction](https://mlsanity.com/paper/2006.03041/) (2020)
- [Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity](https://mlsanity.com/paper/2208.05767/) (2022)
- [Sample Complexity of Robust Reinforcement Learning with a Generative Model](https://mlsanity.com/paper/2112.01506/) (2021)
- [Towards Instance-Optimal Offline Reinforcement Learning with Pessimism](https://mlsanity.com/paper/2110.08695/) (2021)
- [Stochastic approximation with cone-contractive operators: Sharp ℓ_∞-bounds for Q-learning](https://mlsanity.com/paper/1905.06265/) (2019)
- [Finite Time Analysis of Linear Two-timescale Stochastic Approximation with Markovian Noise](https://mlsanity.com/paper/2002.01268/) (2020)
- [Partial Policy Iteration for L1-Robust Markov Decision Processes](https://mlsanity.com/paper/2006.09484/) (2020)
- [On the Fenchel Duality between Strong Convexity and Lipschitz Continuous Gradient](https://mlsanity.com/paper/1803.06573/) (2018)
- [An Online Method for A Class of Distributionally Robust Optimization with Non-Convex Objectives](https://mlsanity.com/paper/2006.10138/) (2020)
- [Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis](https://mlsanity.com/paper/2003.07337/) (2020)
- [Finite-Time Performance Bounds and Adaptive Learning Rate Selection for Two Time-Scale Reinforcement Learning](https://mlsanity.com/paper/1907.06290/) (2019)
- [Non-convex Distributionally Robust Optimization: Non-asymptotic Analysis](https://mlsanity.com/paper/2110.12459/) (2021)
- [Nonlinear Two-Time-Scale Stochastic Approximation: Convergence and Finite-Time Performance](https://mlsanity.com/paper/2011.01868/) (2020)
- [Robust Markov Decision Process: Beyond Rectangularity](https://mlsanity.com/paper/1811.00215/) (2018)
- [A Two-Time-Scale Stochastic Optimization Framework with Applications in Control and Reinforcement Learning](https://mlsanity.com/paper/2109.14756/) (2021)
- [Instance-optimality in optimal value estimation: Adaptivity via variance-reduced Q-learning](https://mlsanity.com/paper/2106.14352/) (2021)
- [Finite-Time Analysis of Stochastic Gradient Descent under Markov Randomness](https://mlsanity.com/paper/2003.10973/) (2020)
- [Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning](https://mlsanity.com/paper/1612.02516/) (2016)
- [Finite-Time Convergence Rates of Nonlinear Two-Time-Scale Stochastic Approximation under Markovian Noise](https://mlsanity.com/paper/2104.01627/) (2021)

## Built on by (most cited first, 11 of 11)

- [Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty](https://mlsanity.com/paper/2404.18909/) (2024)
- [Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning](https://mlsanity.com/paper/2403.09621/) (2024)
- [Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form](https://mlsanity.com/paper/2408.16286/) (2024)
- [Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization](https://mlsanity.com/paper/2411.18612/) (2024)
- [Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees](https://mlsanity.com/paper/2505.19238/) (2025)
- [ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning](https://mlsanity.com/paper/2508.03768/) (2025)
- [Minimax-Optimal Multi-Agent Robust Reinforcement Learning](https://mlsanity.com/paper/2412.19873/) (2024)
- [Model-Free Robust φ-Divergence Reinforcement Learning Using Both Offline and Online Data](https://mlsanity.com/paper/2405.05468/) (2024)
- [TAB-Fields: A Maximum Entropy Framework for Mission-Aware Adversarial Planning](https://mlsanity.com/paper/2412.02570/) (2024)
- [Pessimism Principle Can Be Effective: Towards a Framework for Zero-Shot Transfer Reinforcement Learning](https://mlsanity.com/paper/2505.18447/) (2025)
- [Online Robust Reinforcement Learning with General Function Approximation](https://mlsanity.com/paper/2512.18957/) (2025)

## Abstract (arXiv)

Robust Markov Decision Processes (MDPs) are receiving much attention in learning a robust policy which is less sensitive to environment changes. There are an increasing number of works analyzing sample-efficiency of robust MDPs. However, there are two major barriers to applying robust MDPs in practice. First, most works study robust MDPs in a model-based regime, where the transition probability needs to be estimated and requires a large amount of memories O(|S|2|A|). Second, prior work typically assumes a strong oracle to obtain the optimal solution as an intermediate step to solve robust MDPs. However, in practice, such an oracle does not exist usually. To remove the oracle, we transform the original robust MDPs into an alternative form, which allows us to use stochastic gradient methods to solve the robust MDPs. Moreover, we prove the alternative form still plays a similar role as the original form. With this new formulation, we devise a sample-efficient algorithm to solve the robust MDPs in a model-free regime, which does not require an oracle and trades off a lower storage requirement O(|S||A|) with being able to generate samples from a generative model or Markovian chain. Finally, we validate our theoretical findings via numerical experiments, showing the efficiency with the alternative form of robust MDPs.