Test-time Offline Reinforcement Learning on Goal-related Experience

• URL: http://arxiv.org/abs/2507.18809v1
• Date: Thu, 24 Jul 2025 21:11:39 GMT
• Title: Test-time Offline Reinforcement Learning on Goal-related Experience
• Authors: Marco Bagatella, Mert Albaba, Jonas Hübotter, Georg Martius, Andreas Krause,
• Abstract summary: Research in foundation models has shown that performance can be substantially improved through test-time training.<n>We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state.<n>Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out.
• Score: 50.94457794664909
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this widespread framework and offline goal-conditioned reinforcement learning algorithms: a universal value function is trained on a large number of goals, and the policy is evaluated on a single goal in each test episode. Extensive research in foundation models has shown that performance can be substantially improved through test-time training, specializing the model to the current goal. We find similarly that test-time offline reinforcement learning on experience related to the test goal can lead to substantially better policies at minimal compute costs. We propose a novel self-supervised data selection criterion, which selects transitions from an offline dataset according to their relevance to the current state and quality with respect to the evaluation goal. We demonstrate across a wide range of high-dimensional loco-navigation and manipulation tasks that fine-tuning a policy on the selected data for a few gradient steps leads to significant performance gains over standard offline pre-training. Our goal-conditioned test-time training (GC-TTT) algorithm applies this routine in a receding-horizon fashion during evaluation, adapting the policy to the current trajectory as it is being rolled out. Finally, we study compute allocation at inference, demonstrating that, at comparable costs, GC-TTT induces performance gains that are not achievable by scaling model size.

Related papers

• A Snapshot of Influence: A Local Data Attribution Framework for Online Reinforcement Learning [37.62558445850573]
  We propose an algorithm, iterative influence-based filtering (IIF), for online RL training.<n>IIF reduces sample complexity, speeds up training, and achieves higher returns.<n>These results advance interpretability, efficiency, and effectiveness of online RL.
  arXiv  Detail & Related papers  (2025-05-25T19:25:57Z)
• BoostAdapter: Improving Vision-Language Test-Time Adaptation via Regional Bootstrapping [64.8477128397529]
  We propose a training-required and training-free test-time adaptation framework. We maintain a light-weight key-value memory for feature retrieval from instance-agnostic historical samples and instance-aware boosting samples. We theoretically justify the rationality behind our method and empirically verify its effectiveness on both the out-of-distribution and the cross-domain datasets.
  arXiv  Detail & Related papers  (2024-10-20T15:58:43Z)
• Offline Reinforcement Learning from Datasets with Structured Non-Stationarity [50.35634234137108]
  Current Reinforcement Learning (RL) is often limited by the large amount of data needed to learn a successful policy. We address a novel Offline RL problem setting in which, while collecting the dataset, the transition and reward functions gradually change between episodes but stay constant within each episode. We propose a method based on Contrastive Predictive Coding that identifies this non-stationarity in the offline dataset, accounts for it when training a policy, and predicts it during evaluation.
  arXiv  Detail & Related papers  (2024-05-23T02:41:36Z)
• Statistically Efficient Variance Reduction with Double Policy Estimation for Off-Policy Evaluation in Sequence-Modeled Reinforcement Learning [53.97273491846883]
  We propose DPE: an RL algorithm that blends offline sequence modeling and offline reinforcement learning with Double Policy Estimation. We validate our method in multiple tasks of OpenAI Gym with D4RL benchmarks.
  arXiv  Detail & Related papers  (2023-08-28T20:46:07Z)
• Making Look-Ahead Active Learning Strategies Feasible with Neural Tangent Kernels [6.372625755672473]
  We propose a new method for approximating active learning acquisition strategies that are based on retraining with hypothetically-labeled candidate data points. Although this is usually infeasible with deep networks, we use the neural tangent kernel to approximate the result of retraining.
  arXiv  Detail & Related papers  (2022-06-25T06:13:27Z)
• C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks [133.40619754674066]
  Goal-conditioned reinforcement learning can solve tasks in a wide range of domains, including navigation and manipulation. We propose the distant goal-reaching task by using search at training time to automatically generate intermediate states. E-step corresponds to planning an optimal sequence of waypoints using graph search, while the M-step aims to learn a goal-conditioned policy to reach those waypoints.
  arXiv  Detail & Related papers  (2021-10-22T22:05:31Z)
• MUSBO: Model-based Uncertainty Regularized and Sample Efficient Batch Optimization for Deployment Constrained Reinforcement Learning [108.79676336281211]
  Continuous deployment of new policies for data collection and online learning is either cost ineffective or impractical. We propose a new algorithmic learning framework called Model-based Uncertainty regularized and Sample Efficient Batch Optimization. Our framework discovers novel and high quality samples for each deployment to enable efficient data collection.
  arXiv  Detail & Related papers  (2021-02-23T01:30:55Z)
• Representation Matters: Offline Pretraining for Sequential Decision Making [27.74988221252854]
  In this paper, we consider a slightly different approach to incorporating offline data into sequential decision-making. We find that the use of pretraining with unsupervised learning objectives can dramatically improve the performance of policy learning algorithms.
  arXiv  Detail & Related papers  (2021-02-11T02:38:12Z)

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.