# State Diversity Matters in Offline Behavior Distillation

arXiv: https://arxiv.org/abs/2512.06692 · HTML: https://mlsanity.com/paper/2512.06692/

## Key facts

- Cited by 1 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 44 of its 60 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Placed in

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

## Builds on (most cited first, 30 of 44)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems](https://mlsanity.com/paper/2005.01643/) (2020)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction](https://mlsanity.com/paper/1906.00949/) (2019)
- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [MOPO: Model-based Offline Policy Optimization](https://mlsanity.com/paper/2005.13239/) (2020)
- [MOReL : Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2005.05951/) (2020)
- [Dataset Condensation with Gradient Matching](https://mlsanity.com/paper/2006.05929/) (2020)
- [Dataset Distillation by Matching Training Trajectories](https://mlsanity.com/paper/2203.11932/) (2022)
- [COMBO: Conservative Offline Model-Based Policy Optimization](https://mlsanity.com/paper/2102.08363/) (2021)
- [Dataset Condensation with Differentiable Siamese Augmentation](https://mlsanity.com/paper/2102.08259/) (2021)
- [Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning](https://mlsanity.com/paper/2303.05479/) (2023)
- [Dataset Distillation](https://mlsanity.com/paper/1811.10959/) (2018)
- [Scaling Up Dataset Distillation to ImageNet-1K with Constant Memory](https://mlsanity.com/paper/2211.10586/) (2022)
- [Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage](https://mlsanity.com/paper/2107.06226/) (2021)
- [Graph Condensation for Graph Neural Networks](https://mlsanity.com/paper/2110.07580/) (2021)
- [Offline RL for Natural Language Generation with Implicit Language Q Learning](https://mlsanity.com/paper/2206.11871/) (2022)
- [Dataset Distillation: A Comprehensive Review](https://mlsanity.com/paper/2301.07014/) (2023)
- [Revisiting the Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2305.09836/) (2023)
- [Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement Learning](https://mlsanity.com/paper/2202.11566/) (2022)
- [CORL: Research-oriented Deep Offline Reinforcement Learning Library](https://mlsanity.com/paper/2210.07105/) (2022)
- [RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning](https://mlsanity.com/paper/2204.12581/) (2022)
- [A Comprehensive Survey of Dataset Distillation](https://mlsanity.com/paper/2301.05603/) (2023)
- [Remember the Past: Distilling Datasets into Addressable Memories for Neural Networks](https://mlsanity.com/paper/2206.02916/) (2022)
- [Condensing Graphs via One-Step Gradient Matching](https://mlsanity.com/paper/2206.07746/) (2022)

## Built on by (most cited first, 1 of 1)

- [Offline Behavioral Data Selection](https://mlsanity.com/paper/2512.18246/) (2025)

## Abstract (arXiv)

Offline Behavior Distillation (OBD), which condenses massive offline RL data into a compact synthetic behavioral dataset, offers a promising approach for efficient policy training and can be applied across various downstream RL tasks. In this paper, we uncover a misalignment between original and distilled datasets, observing that a high-quality original dataset does not necessarily yield a superior synthetic dataset. Through an empirical analysis of policy performance under varying levels of training loss, we show that datasets with greater state diversity outperforms those with higher state quality when training loss is substantial, as is often the case in OBD, whereas the relationship reverses under minimal loss, which contributes to the misalignment. By associating state quality and diversity in reducing pivotal and surrounding error, respectively, our theoretical analysis establishes that surrounding error plays a more crucial role in policy performance when pivotal error is large, thereby highlighting the importance of state diversity in OBD scenario. Furthermore, we propose a novel yet simple algorithm, state density weighted (SDW) OBD, which emphasizes state diversity by weighting the distillation objective using the reciprocal of state density, thereby distilling a more diverse state information into synthetic data. Extensive experiments across multiple D4RL datasets confirm that SDW significantly enhances OBD performance when the original dataset exhibits limited state diversity.