# ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning

arXiv: https://arxiv.org/abs/2508.03768 · HTML: https://mlsanity.com/paper/2508.03768/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in RL theory and sample complexity, one of 15 directions in Deep reinforcement learning methods.
- Builds on 84 of its 119 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Placed in

- Deep reinforcement learning methods / [RL theory and sample complexity](https://mlsanity.com/deeprl/rl-theory-and-sample-complexity/)

## Builds on (most cited first, 30 of 84)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Training Diffusion Models with Reinforcement Learning](https://mlsanity.com/paper/2305.13301/) (2023)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Provably Efficient Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/1907.05388/) (2019)
- [Minimax Regret Bounds for Reinforcement Learning](https://mlsanity.com/paper/1703.05449/) (2017)
- [Is Q-learning Provably Efficient?](https://mlsanity.com/paper/1807.03765/) (2018)
- [Robust Adversarial Reinforcement Learning](https://mlsanity.com/paper/1703.02702/) (2017)
- [Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey](https://mlsanity.com/paper/2009.13303/) (2020)
- [Risk-Constrained Reinforcement Learning with Percentile Risk Criteria](https://mlsanity.com/paper/1512.01629/) (2015)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [StarCraft II: A New Challenge for Reinforcement Learning](https://mlsanity.com/paper/1708.04782/) (2017)
- [CAD2RL: Real Single-Image Flight without a Single Real Image](https://mlsanity.com/paper/1611.04201/) (2016)
- [Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms](https://mlsanity.com/paper/2102.00815/) (2021)
- [Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes](https://mlsanity.com/paper/2012.08507/) (2020)
- [Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds](https://mlsanity.com/paper/1901.00210/) (2019)
- [Guiding Pretraining in Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2302.06692/) (2023)
- [Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning](https://mlsanity.com/paper/1703.07710/) (2017)
- [Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach](https://mlsanity.com/paper/1506.02188/) (2015)
- [Tactics of Adversarial Attack on Deep Reinforcement Learning Agents](https://mlsanity.com/paper/1703.06748/) (2017)
- [Robust Deep Reinforcement Learning with Adversarial Attacks](https://mlsanity.com/paper/1712.03632/) (2017)
- [EPOpt: Learning Robust Neural Network Policies Using Model Ensembles](https://mlsanity.com/paper/1610.01283/) (2016)
- [Almost Optimal Model-Free Reinforcement Learning via Reference-Advantage Decomposition](https://mlsanity.com/paper/2004.10019/) (2020)
- [Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods](https://mlsanity.com/paper/2404.00282/) (2024)
- [Episodic Reinforcement Learning in Finite MDPs: Minimax Lower Bounds Revisited](https://mlsanity.com/paper/2010.03531/) (2020)
- [Delving into adversarial attacks on deep policies](https://mlsanity.com/paper/1705.06452/) (2017)
- [Supervised Reinforcement Learning with Recurrent Neural Network for Dynamic Treatment Recommendation](https://mlsanity.com/paper/1807.01473/) (2018)

## Built on by (most cited first, 6 of 6)

- [Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation](https://mlsanity.com/paper/2510.01721/) (2025)
- [Stress-Aware Learning under KL Drift via Trust-Decayed Mirror Descent](https://mlsanity.com/paper/2510.15222/) (2025)
- [Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs](https://mlsanity.com/paper/2605.24345/) (2026)
- [Stationary Robust Mean-Field Games under Model Mismatches](https://mlsanity.com/paper/2606.22579/) (2026)
- [Statistical Convergence of Transformer Encoder-Accelerated Robust Reinforcement Learning](https://mlsanity.com/paper/2609.23775/) (2026)
- [Interactive Distributionally Robust Multi-Agent Learning with General Function Approximation](https://mlsanity.com/paper/2609.32048/) (2026)

## Abstract (arXiv)

We investigate reinforcement learning (RL) in the presence of distributional mismatch between training and deployment, where policies trained in simulators often underperform in practice due to mismatches between training and deployment conditions, and thereby reliable guarantees on real-world performance are essential. Distributionally robust RL addresses this issue by optimizing worst-case performance over an uncertainty set of environments and providing an optimized lower bound on deployment performance. However, existing studies typically assume access to either a generative model or offline datasets with broad coverage of the deployment environment-assumptions that limit their practicality in unknown environments without prior knowledge. In this work, we study a more practical and challenging setting: online distributionally robust RL, where the agent interacts only with a single unknown training environment while seeking policies that are robust with respect to an uncertainty set around this nominal model. We consider general f-divergence-based ambiguity sets, including chi2 and KL divergence balls, and design a computationally efficient algorithm that achieves sublinear regret for the robust control objective under minimal assumptions, without requiring generative or offline data access. Moreover, we establish a corresponding minimax lower bound on the regret of any online algorithm, demonstrating the near-optimality of our method. Experiments across diverse environments with model misspecification show that our approach consistently improves worst-case performance and aligns with the theoretical guarantees.