# Boosting Offline Reinforcement Learning with Action Preference Query

arXiv: https://arxiv.org/abs/2306.03362 · HTML: https://mlsanity.com/paper/2306.03362/

## Key facts

- Cited by 12 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 30 of its 57 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## 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 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [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)
- [OpenAI Gym](https://mlsanity.com/paper/1606.01540/) (2016)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [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)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning](https://mlsanity.com/paper/1910.00177/) (2019)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [AWAC: Accelerating Online Reinforcement Learning with Offline Datasets](https://mlsanity.com/paper/2006.09359/) (2020)
- [Behavior Regularized Offline Reinforcement Learning](https://mlsanity.com/paper/1911.11361/) (2019)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [Critic Regularized Regression](https://mlsanity.com/paper/2006.15134/) (2020)
- [Offline Reinforcement Learning with Fisher Divergence Critic Regularization](https://mlsanity.com/paper/2103.08050/) (2021)
- [A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems](https://mlsanity.com/paper/2203.01387/) (2022)
- [EMaQ: Expected-Max Q-Learning Operator for Simple Yet Effective Offline and Online RL](https://mlsanity.com/paper/2007.11091/) (2020)
- [Diagnosing Bottlenecks in Deep Q-learning Algorithms](https://mlsanity.com/paper/1902.10250/) (2019)
- [DisCor: Corrective Feedback in Reinforcement Learning via Distribution Correction](https://mlsanity.com/paper/2003.07305/) (2020)
- [Reinforcement Learning for Education: Opportunities and Challenges](https://mlsanity.com/paper/2107.08828/) (2021)
- [Boosting Offline Reinforcement Learning via Data Rebalancing](https://mlsanity.com/paper/2210.09241/) (2022)
- [TOHAN: A One-step Approach towards Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2106.06326/) (2021)
- [Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning](https://mlsanity.com/paper/2206.12542/) (2022)
- [Dynamic Knowledge Distillation for Black-box Hypothesis Transfer Learning](https://mlsanity.com/paper/2007.12355/) (2020)

## Built on by (most cited first, 12 of 12)

- [Rank-DETR for High Quality Object Detection](https://mlsanity.com/paper/2310.08854/) (2023)
- [Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning](https://mlsanity.com/paper/2310.17966/) (2023)
- [Efficient Diffusion Transformer with Step-wise Dynamic Attention Mediators](https://mlsanity.com/paper/2408.05710/) (2024)
- [Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL](https://mlsanity.com/paper/2310.04411/) (2023)
- [Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning](https://mlsanity.com/paper/2405.19909/) (2024)
- [Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation](https://mlsanity.com/paper/2310.17146/) (2023)
- [Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials](https://mlsanity.com/paper/2511.00833/) (2025)
- [Integrating Domain Knowledge for handling Limited Data in Offline RL](https://mlsanity.com/paper/2406.07041/) (2024)
- [Imagination-Limited Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2505.12211/) (2025)
- [Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning](https://mlsanity.com/paper/2508.19900/) (2025)
- [How well can LLMs provide planning feedback in grounded environments?](https://mlsanity.com/paper/2509.09790/) (2025)
- [Conservative Query and Adaptive Regularization for Offline RL Under Uncertainty Estimation](https://mlsanity.com/paper/2607.19199/) (2026)

## Abstract (arXiv)

Training practical agents usually involve offline and online reinforcement learning (RL) to balance the policy's performance and interaction costs. In particular, online fine-tuning has become a commonly used method to correct the erroneous estimates of out-of-distribution data learned in the offline training phase. However, even limited online interactions can be inaccessible or catastrophic for high-stake scenarios like healthcare and autonomous driving. In this work, we introduce an interaction-free training scheme dubbed Offline-with-Action-Preferences (OAP). The main insight is that, compared to online fine-tuning, querying the preferences between pre-collected and learned actions can be equally or even more helpful to the erroneous estimate problem. By adaptively encouraging or suppressing policy constraint according to action preferences, OAP could distinguish overestimation from beneficial policy improvement and thus attains a more accurate evaluation of unseen data. Theoretically, we prove a lower bound of the behavior policy's performance improvement brought by OAP. Moreover, comprehensive experiments on the D4RL benchmark and state-of-the-art algorithms demonstrate that OAP yields higher (29% on average) scores, especially on challenging AntMaze tasks (98% higher).