Behavior-Adaptive Q-Learning: A Unifying Framework for Offline-to-Online RL

• URL: http://arxiv.org/abs/2511.03695v1
• Date: Wed, 05 Nov 2025 18:20:23 GMT
• Title: Behavior-Adaptive Q-Learning: A Unifying Framework for Offline-to-Online RL
• Authors: Lipeng Zu, Hansong Zhou, Xiaonan Zhang,
• Abstract summary: We introduce Behavior-Adaptive Q-Learning (BAQ), a framework designed to enable a smooth transition from offline to online RL.<n>BAQ incorporates a dual-objective loss that (i) aligns the online policy toward the offline behavior when uncertainty is high, and (ii) gradually relaxes this constraint as more confident online experience is accumulated.<n>Across standard benchmarks, BAQ consistently outperforms prior offline-to-online RL approaches, achieving faster recovery, improved robustness, and higher overall performance.
• Score: 3.2883573376133555
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Offline reinforcement learning (RL) enables training from fixed data without online interaction, but policies learned offline often struggle when deployed in dynamic environments due to distributional shift and unreliable value estimates on unseen state-action pairs. We introduce Behavior-Adaptive Q-Learning (BAQ), a framework designed to enable a smooth and reliable transition from offline to online RL. The key idea is to leverage an implicit behavioral model derived from offline data to provide a behavior-consistency signal during online fine-tuning. BAQ incorporates a dual-objective loss that (i) aligns the online policy toward the offline behavior when uncertainty is high, and (ii) gradually relaxes this constraint as more confident online experience is accumulated. This adaptive mechanism reduces error propagation from out-of-distribution estimates, stabilizes early online updates, and accelerates adaptation to new scenarios. Across standard benchmarks, BAQ consistently outperforms prior offline-to-online RL approaches, achieving faster recovery, improved robustness, and higher overall performance. Our results demonstrate that implicit behavior adaptation is a principled and practical solution for reliable real-world policy deployment.

Related papers

• Human-in-the-loop Online Rejection Sampling for Robotic Manipulation [55.99788088622936]
  Hi-ORS stabilizes value estimation by filtering out negatively rewarded samples during online fine-tuning.<n>Hi-ORS fine-tunes a pi-base policy to master contact-rich manipulation in just 1.5 hours of real-world training.
  arXiv  Detail & Related papers  (2025-10-30T11:53:08Z)
• A Perspective of Q-value Estimation on Offline-to-Online Reinforcement Learning [54.48409201256968]
  offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online samples. Most O2O methods focus on the balance between RL objective and pessimism, or the utilization of offline and online samples.
  arXiv  Detail & Related papers  (2023-12-12T19:24:35Z)
• Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning [71.02384943570372]
  Family Offline-to-Online RL (FamO2O) is a framework that empowers existing algorithms to determine state-adaptive improvement-constraint balances. FamO2O offers a statistically significant improvement over various existing methods, achieving state-of-the-art performance on the D4RL benchmark.
  arXiv  Detail & Related papers  (2023-10-27T08:30:54Z)
• Towards Robust Offline-to-Online Reinforcement Learning via Uncertainty and Smoothness [11.241036026084222]
  offline-to-online (O2O) RL provides a paradigm for improving an offline trained agent within limited online interactions. Most offline RL algorithms suffer from performance drops and fail to achieve stable policy improvement in O2O adaptation. We propose the Robust Offline-to-Online (RO2O) algorithm, designed to enhance offline policies through uncertainty and smoothness.
  arXiv  Detail & Related papers  (2023-09-29T04:42:50Z)
• A Simple Unified Uncertainty-Guided Framework for Offline-to-Online Reinforcement Learning [25.123237633748193]
  offline-to-online reinforcement learning can be challenging due to constrained exploratory behavior and state-action distribution shift. We propose a Simple Unified uNcertainty-Guided (SUNG) framework, which unifies the solution to both challenges with the tool of uncertainty. SUNG achieves state-of-the-art online finetuning performance when combined with different offline RL methods.
  arXiv  Detail & Related papers  (2023-06-13T05:22:26Z)
• ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles [52.34951901588738]
  We propose a novel framework called ENsemble-based Offline-To-Online (ENOTO) RL. By increasing the number of Q-networks, we seamlessly bridge offline pre-training and online fine-tuning without degrading performance. Experimental results demonstrate that ENOTO can substantially improve the training stability, learning efficiency, and final performance of existing offline RL methods.
  arXiv  Detail & Related papers  (2023-06-12T05:10:10Z)
• Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning [80.25648265273155]
  Offline reinforcement learning, by learning from a fixed dataset, makes it possible to learn agent behaviors without interacting with the environment. During online fine-tuning, the performance of the pre-trained agent may collapse quickly due to the sudden distribution shift from offline to online data. We propose to adaptively weigh the behavior cloning loss during online fine-tuning based on the agent's performance and training stability. Experiments show that the proposed method yields state-of-the-art offline-to-online reinforcement learning performance on the popular D4RL benchmark.
  arXiv  Detail & Related papers  (2022-10-25T09:08:26Z)
• Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning [62.19209005400561]
  offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets. A key challenge of offline RL is the instability of policy training, caused by the mismatch between the distribution of the offline data and the undiscounted stationary state-action distribution of the learned policy. We regularize the undiscounted stationary distribution of the current policy towards the offline data during the policy optimization process.
  arXiv  Detail & Related papers  (2022-06-14T20:56:16Z)
• MOORe: Model-based Offline-to-Online Reinforcement Learning [26.10368749930102]
  We propose a model-based Offline-to-Online Reinforcement learning (MOORe) algorithm. Experiment results show that our algorithm smoothly transfers from offline to online stages while enabling sample-efficient online adaption.
  arXiv  Detail & Related papers  (2022-01-25T03:14:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.