# Online KL-Regularized Reinforcement Learning with Function Approximation under Misspecification

arXiv: https://arxiv.org/abs/2606.06053 · HTML: https://mlsanity.com/paper/2606.06053/

## Key facts

- Cited by 3 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 28 of its 33 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## 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, 28 of 28)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Provably Efficient Reinforcement Learning with Linear Function Approximation](https://mlsanity.com/paper/1907.05388/) (2019)
- [Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraint](https://mlsanity.com/paper/2312.11456/) (2023)
- [Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms](https://mlsanity.com/paper/2102.00815/) (2021)
- [Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits](https://mlsanity.com/paper/1402.0555/) (2014)
- [Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles](https://mlsanity.com/paper/2002.04926/) (2020)
- [Exploratory Preference Optimization: Harnessing Implicit Q*-Approximation for Sample-Efficient RLHF](https://mlsanity.com/paper/2405.21046/) (2024)
- [Is RLHF More Difficult than Standard RL?](https://mlsanity.com/paper/2306.14111/) (2023)
- [Practical Contextual Bandits with Regression Oracles](https://mlsanity.com/paper/1803.01088/) (2018)
- [The Role of Coverage in Online Reinforcement Learning](https://mlsanity.com/paper/2210.04157/) (2022)
- [Adapting to Misspecification in Contextual Bandits](https://mlsanity.com/paper/2107.05745/) (2021)
- [Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective](https://mlsanity.com/paper/2010.03104/) (2020)
- [Value-Incentivized Preference Optimization: A Unified Approach to Online and Offline RLHF](https://mlsanity.com/paper/2405.19320/) (2024)
- [Preference-based Reinforcement Learning with Finite-Time Guarantees](https://mlsanity.com/paper/2006.08910/) (2020)
- [Online Iterative Reinforcement Learning from Human Feedback with General Preference Model](https://mlsanity.com/paper/2402.07314/) (2024)
- [Sharp Analysis for KL-Regularized Contextual Bandits and RLHF](https://mlsanity.com/paper/2411.04625/) (2024)
- [Logarithmic Regret for Online KL-Regularized Reinforcement Learning](https://mlsanity.com/paper/2502.07460/) (2025)
- [Adapting to Misspecification in Contextual Bandits with Offline Regression Oracles](https://mlsanity.com/paper/2102.13240/) (2021)
- [Greedy Sampling Is Provably Efficient for RLHF](https://mlsanity.com/paper/2510.24700/) (2025)
- [On the Model-Misspecification in Reinforcement Learning](https://mlsanity.com/paper/2306.10694/) (2023)
- [Improved Algorithms for Misspecified Linear Markov Decision Processes](https://mlsanity.com/paper/2109.05546/) (2021)
- [Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback](https://mlsanity.com/paper/2510.09127/) (2025)
- [Provably Efficient Regularized Online RLHF with Generalized Bilinear Preferences](https://mlsanity.com/paper/2602.23116/) (2026)
- [Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning](https://mlsanity.com/paper/2401.12216/) (2024)
- [Taming the Monster Every Context: Complexity Measure and Unified Framework for Offline-Oracle Efficient Contextual Bandits](https://mlsanity.com/paper/2602.09456/) (2026)
- [Optimal Regret for Policy Optimization in Contextual Bandits](https://mlsanity.com/paper/2602.13700/) (2026)

## Built on by (most cited first, 3 of 3)

- [When Greedy Sampling Explores: KL-Regularized Contextual Bandits without Eluder-Dimension Dependence](https://mlsanity.com/paper/2609.13564/) (2026)
- [Understanding Off- vs On-Policy Distillation: A Tale of Distinct Training Objectives](https://mlsanity.com/paper/2609.38666/) (2026)
- [Fast Rates for Offline Q-Learning with KL Regularization](https://mlsanity.com/paper/2610.18839/) (2026)

## Abstract (arXiv)

We study KL-regularized contextual bandits and episodic reinforcement learning (RL) under general function approximation with model misspecification. Existing guarantees rely on realizability and therefore do not extend to misspecified models, where classical regret bounds may fail. This work introduces KL misspecification formulations for contextual bandits and episodic RL and analyzes regression-based algorithms with Gibbs policy updates. High-probability KL-regret guarantees with explicit misspecification terms are established, recovering the standard realizable KL-regularized setting as a special case.