In-Context Compositional Q-Learning for Offline Reinforcement Learning

• URL: http://arxiv.org/abs/2509.24067v1
• Date: Sun, 28 Sep 2025 20:55:21 GMT
• Title: In-Context Compositional Q-Learning for Offline Reinforcement Learning
• Authors: Qiushui Xu, Yuhao Huang, Yushu Jiang, Lei Song, Jinyu Wang, Wenliang Zheng, Jiang Bian,
• Abstract summary: We propose In-context Compositional Q-Learning (textttICQL), the first offline RL framework that formulates Q-learning as a contextual inference problem.<n>We show that under two assumptions--linear approximability of the local Q-function and accurate weight inference--textttICQL achieves bounded Q-function approximation error.<n> Empirically, textttICQL substantially improves performance in offline settings.
• Score: 21.45273716299317
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurately estimating the Q-function is a central challenge in offline reinforcement learning. However, existing approaches often rely on a single global Q-function, which struggles to capture the compositional nature of tasks involving diverse subtasks. We propose In-context Compositional Q-Learning (\texttt{ICQL}), the first offline RL framework that formulates Q-learning as a contextual inference problem, using linear Transformers to adaptively infer local Q-functions from retrieved transitions without explicit subtask labels. Theoretically, we show that under two assumptions--linear approximability of the local Q-function and accurate weight inference from retrieved context--\texttt{ICQL} achieves bounded Q-function approximation error, and supports near-optimal policy extraction. Empirically, \texttt{ICQL} substantially improves performance in offline settings: improving performance in kitchen tasks by up to 16.4\%, and in Gym and Adroit tasks by up to 8.6\% and 6.3\%. These results highlight the underexplored potential of in-context learning for robust and compositional value estimation, positioning \texttt{ICQL} as a principled and effective framework for offline RL.

Related papers

• Q-learning with Adjoint Matching [58.78551025170267]
  We propose Q-learning with Adjoint Matching (QAM), a novel TD-based reinforcement learning (RL) algorithm.<n>QAM sidesteps two challenges by leveraging adjoint matching, a recently proposed technique in generative modeling.<n>It consistently outperforms prior approaches on hard, sparse reward tasks in both offline and offline-to-online RL.
  arXiv  Detail & Related papers  (2026-01-20T18:45:34Z)
• BiCQL-ML: A Bi-Level Conservative Q-Learning Framework for Maximum Likelihood Inverse Reinforcement Learning [10.016258281947122]
  BiCQL-ML is a policy-free offline inverse reinforcement learning algorithm.<n>We show BiCQL-ML improves both reward recovery and downstream policy performance.
  arXiv  Detail & Related papers  (2025-11-27T08:27:10Z)
• Continual Action Quality Assessment via Adaptive Manifold-Aligned Graph Regularization [53.82400605816587]
  Action Quality Assessment (AQA) quantifies human actions in videos, supporting applications in sports scoring, rehabilitation, and skill evaluation.<n>A major challenge lies in the non-stationary nature of quality distributions in real-world scenarios.<n>We introduce Continual AQA (CAQA), which equips with Continual Learning capabilities to handle evolving distributions.
  arXiv  Detail & Related papers  (2025-10-08T10:09:47Z)
• Scalable In-Context Q-Learning [68.9917436397079]
  We propose textbfScalable textbfIn-textbfContext textbfQ-textbfLearning (textbfSICQL) to steer in-context reinforcement learning.<n>textbfSICQL harnesses dynamic programming and world modeling to steer ICRL toward efficient reward and task generalization.
  arXiv  Detail & Related papers  (2025-06-02T04:21:56Z)
• Q-function Decomposition with Intervention Semantics with Factored Action Spaces [51.01244229483353]
  We consider Q-functions defined over a lower dimensional projected subspace of the original action space, and study the condition for the unbiasedness of decomposed Q-functions.<n>This leads to a general scheme which we call action decomposed reinforcement learning that uses the projected Q-functions to approximate the Q-function in standard model-free reinforcement learning algorithms.
  arXiv  Detail & Related papers  (2025-04-30T05:26:51Z)
• Learning Task Representations from In-Context Learning [73.72066284711462]
  Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning.<n>We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads.<n>We show that our method's effectiveness stems from aligning the distribution of the last hidden state with that of an optimally performing in-context-learned model.
  arXiv  Detail & Related papers  (2025-02-08T00:16:44Z)
• ACL-QL: Adaptive Conservative Level in Q-Learning for Offline Reinforcement Learning [46.67828766038463]
  We propose a framework, Adaptive Conservative Level in Q-Learning (ACL-QL), which limits the Q-values in a mild range.<n>ACL-QL enables adaptive control on the conservative level over each state-action pair, i.e., lifting the Q-values more for good transitions and less for bad transitions.<n>Motivated by the theoretical analysis, we propose a novel algorithm, ACL-QL, which uses two learnable adaptive weight functions to control the conservative level over each transition.
  arXiv  Detail & Related papers  (2024-12-22T04:18:02Z)
• VerifierQ: Enhancing LLM Test Time Compute with Q-Learning-based Verifiers [7.7705926659081275]
  VerifierQ is a novel approach that integrates Offline Q-learning into verifier models. We address three key challenges in applying Q-learning to LLMs. Our method enables parallel Q-value computation and improving training efficiency.
  arXiv  Detail & Related papers  (2024-10-10T15:43:55Z)
• Online Target Q-learning with Reverse Experience Replay: Efficiently finding the Optimal Policy for Linear MDPs [50.75812033462294]
  We bridge the gap between practical success of Q-learning and pessimistic theoretical results. We present novel methods Q-Rex and Q-RexDaRe. We show that Q-Rex efficiently finds the optimal policy for linear MDPs.
  arXiv  Detail & Related papers  (2021-10-16T01:47:41Z)
• Conservative Q-Learning for Offline Reinforcement Learning [106.05582605650932]
  We show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a policy learning procedure with theoretical improvement guarantees.
  arXiv  Detail & Related papers  (2020-06-08T17:53:42Z)

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.