# Robust Offline Reinforcement Learning with Linearly Structured f-Divergence Regularization

arXiv: https://arxiv.org/abs/2411.18612 · HTML: https://mlsanity.com/paper/2411.18612/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Offline RL algorithms, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 27 Nov 2024.

## Placed in

- Offline RL and imitation learning from data / [Offline RL algorithms](https://mlsanity.com/offlinerl/offline-rl-algorithms/)

## Builds on (most cited first, 22 of 22)

- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Provably Efficient Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/1907.05388/) (2019)
- [Is Pessimism Provably Efficient for Offline RL?](https://mlsanity.com/paper/2012.15085/) (2020)
- [Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations](https://mlsanity.com/paper/2003.08938/) (2020)
- [Assessing Generalization in Deep Reinforcement Learning](https://mlsanity.com/paper/1810.12282/) (2018)
- [Robust Reinforcement Learning using Offline Data](https://mlsanity.com/paper/2208.05129/) (2022)
- [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)
- [Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game](https://mlsanity.com/paper/2205.15512/) (2022)
- [The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model](https://mlsanity.com/paper/2305.16589/) (2023)
- [Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage](https://mlsanity.com/paper/2305.09659/) (2023)
- [Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning](https://mlsanity.com/paper/2303.02783/) (2023)
- [Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/2209.06620/) (2022)
- [Distributionally Robust Off-Dynamics Reinforcement Learning: Provable Efficiency with Linear Function Approximation](https://mlsanity.com/paper/2402.15399/) (2024)
- [Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning](https://mlsanity.com/paper/2403.09621/) (2024)
- [Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity](https://mlsanity.com/paper/2306.11626/) (2023)
- [Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation](https://mlsanity.com/paper/2411.09891/) (2024)
- [Upper and Lower Bounds for Distributionally Robust Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2409.20521/) (2024)
- [Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes](https://mlsanity.com/paper/2403.12946/) (2024)
- [Return Augmented Decision Transformer for Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2410.23450/) (2024)
- [Bridging Distributionally Robust Learning and Offline RL: An Approach to Mitigate Distribution Shift and Partial Data Coverage](https://mlsanity.com/paper/2310.18434/) (2023)
- [Robust Markov Decision Processes without Model Estimation](https://mlsanity.com/paper/2302.01248/) (2023)

## Built on by (most cited first, 8 of 8)

- [MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning](https://mlsanity.com/paper/2506.08460/) (2025)
- [ORVIT: Near-Optimal Online Distributionally Robust Reinforcement Learning](https://mlsanity.com/paper/2508.03768/) (2025)
- [Linear Mixture Distributionally Robust Markov Decision Processes](https://mlsanity.com/paper/2505.18044/) (2025)
- [Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality](https://mlsanity.com/paper/2508.17448/) (2025)
- [Online Robust Reinforcement Learning with General Function Approximation](https://mlsanity.com/paper/2512.18957/) (2025)
- [Robust Data-Collection Policy Learning for Low-Variance Online Policy Evaluation](https://mlsanity.com/paper/2608.24146/) (2026)
- [Finite-Time Convergence of Single-Trajectory Chi-Square Robust Q-Learning With Linear Function Approximation](https://mlsanity.com/paper/2510.01721/) (2025)
- [Cross-Domain Energy-Guided Diffusion Generation for Off-Dynamics Reinforcement Learning](https://mlsanity.com/paper/2605.24810/) (2026)

## Abstract (arXiv)

The Robust Regularized Markov Decision Process (RRMDP) is proposed to learn policies robust to dynamics shifts by adding regularization to the transition dynamics in the value function. Existing methods mostly use unstructured regularization, potentially leading to conservative policies under unrealistic transitions. To address this limitation, we propose a novel framework, the d-rectangular linear RRMDP (d-RRMDP), which introduces latent structures into both transition kernels and regularization. We focus on offline reinforcement learning, where an agent learns policies from a precollected dataset in the nominal environment. We develop the Robust Regularized Pessimistic Value Iteration (R2PVI) algorithm that employs linear function approximation for robust policy learning in d-RRMDPs with f-divergence based regularization terms on transition kernels. We provide instance-dependent upper bounds on the suboptimality gap of R2PVI policies, demonstrating that these bounds are influenced by how well the dataset covers state-action spaces visited by the optimal robust policy under robustly admissible transitions. We establish information-theoretic lower bounds to verify that our algorithm is near-optimal. Finally, numerical experiments validate that R2PVI learns robust policies and exhibits superior computational efficiency compared to baseline methods.