English
Related papers

Related papers: Test-time Offline Reinforcement Learning on Goal-r…

200 papers

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau…

Machine Learning · Computer Science 2026-04-22 Qingyang Zhang , Xinke Kong , Haitao Wu , Qinghua Hu , Minghao Wu , Baosong Yang , Yu Cheng , Yun Luo , Ganqu Cui , Changqing Zhang

Rapid development of large-scale pre-training has resulted in foundation models that can act as effective feature extractors on a variety of downstream tasks and domains. Motivated by this, we study the efficacy of pre-trained vision models…

Machine Learning · Computer Science 2022-07-05 Oleksiy Ostapenko , Timothee Lesort , Pau Rodríguez , Md Rifat Arefin , Arthur Douillard , Irina Rish , Laurent Charlin

Large language models are typically post-trained using supervised fine-tuning (SFT) and reinforcement learning (RL), yet effectively unifying efficient knowledge injection with robust generalization remains challenging. In this work, we…

Artificial Intelligence · Computer Science 2026-05-05 Wangjie Gan , Miao Pan , Linbo Xi , Wenqi Zhang , Jintao Chen , Jianwei Yin , Xuhong Zhang

The potential of offline reinforcement learning (RL) is that high-capacity models trained on large, heterogeneous datasets can lead to agents that generalize broadly, analogously to similar advances in vision and NLP. However, recent works…

Machine Learning · Computer Science 2023-04-19 Aviral Kumar , Rishabh Agarwal , Xinyang Geng , George Tucker , Sergey Levine

Generalizing deep learning models to unknown target domain distribution with low latency has motivated research into test-time training/adaptation (TTT/TTA). Existing approaches often focus on improving test-time training performance under…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Yushu Li , Xun Xu , Yongyi Su , Kui Jia

Recent work in offline reinforcement learning (RL) has demonstrated the effectiveness of formulating decision-making as return-conditioned supervised learning. Notably, the decision transformer (DT) architecture has shown promise across…

Machine Learning · Computer Science 2025-04-04 Tung M. Luu , Donghoon Lee , Chang D. Yoo

Goal-conditioned policies enable decision-making models to execute diverse behaviors based on specified goals, yet their downstream performance is often highly sensitive to the choice of instructions or prompts. To bypass the limitations of…

Artificial Intelligence · Computer Science 2026-05-04 Guangyu Zhao , Kewei Lian , Haoxuan Ru , Borong Zhang , Haowei Lin , Zhancun Mu , Haobo Fu , Qiang Fu , Shaofei Cai , Zihao Wang , Yitao Liang

Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Justin Fu , Marvin Zhang , Sergey Levine

Leveraging offline data is a promising way to improve the sample efficiency of online reinforcement learning (RL). This paper expands the pool of usable data for offline-to-online RL by leveraging abundant non-curated data that is…

Machine Learning · Computer Science 2025-05-20 Yi Zhao , Aidan Scannell , Wenshuai Zhao , Yuxin Hou , Tianyu Cui , Le Chen , Dieter Büchler , Arno Solin , Juho Kannala , Joni Pajarinen

Goal-conditioned reinforcement learning endows an agent with a large variety of skills, but it often struggles to solve tasks that require more temporally extended reasoning. In this work, we propose to incorporate imagined subgoals into…

Machine Learning · Computer Science 2021-07-02 Elliot Chane-Sane , Cordelia Schmid , Ivan Laptev

The robustness of any machine learning solution is fundamentally bound by the data it was trained on. One way to generalize beyond the original training is through human-informed augmentation of the original dataset; however, it is…

Machine Learning · Computer Science 2022-09-08 Nicholas A. Ketz , Praveen K. Pilly

Offline goal-conditioned reinforcement learning (GCRL) can be challenging due to overfitting to the given dataset. To generalize agents' skills outside the given dataset, we propose a goal-swapping procedure that generates additional…

Machine Learning · Computer Science 2023-02-20 Wenyan Yang , Huiling Wang , Dingding Cai , Joni Pajarinen , Joni-Kristen Kämäräinen

Reinforcement learning faces significant challenges when applied to tasks characterized by sparse reward structures. Although imitation learning, within the domain of supervised learning, offers faster convergence, it relies heavily on…

Machine Learning · Computer Science 2025-09-04 Zeqiang Zhang , Fabian Wurzberger , Gerrit Schmid , Sebastian Gottwald , Daniel A. Braun

Learning to adapt pretrained language models to unlabeled, out-of-distribution data is a critical challenge, as models often falter on structurally novel reasoning tasks even while excelling within their training distribution. We introduce…

Computation and Language · Computer Science 2025-05-29 Mohammad Mahdi Moradi , Hossam Amer , Sudhir Mudur , Weiwei Zhang , Yang Liu , Walid Ahmed

Recent advancements in offline reinforcement learning (RL) have underscored the capabilities of Return-Conditioned Supervised Learning (RCSL), a paradigm that learns the action distribution based on target returns for each state in a…

Machine Learning · Computer Science 2023-12-22 Yuanfu Wang , Chao Yang , Ying Wen , Yu Liu , Yu Qiao

Reinforcement learning (RL) is typically concerned with estimating stationary policies or single-step models, leveraging the Markov property to factorize problems in time. However, we can also view RL as a generic sequence modeling problem,…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Qiyang Li , Sergey Levine

This article provides a rigorous analysis of convergence and stability of Episodic Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning and Online Decision Transformers. These algorithms performed competitively across…

Learning the value function of a given policy (target policy) from the data samples obtained from a different policy (behavior policy) is an important problem in Reinforcement Learning (RL). This problem is studied under the setting of…

Machine Learning · Computer Science 2019-11-14 Raghuram Bharadwaj Diddigi , Chandramouli Kamanchi , Shalabh Bhatnagar

Despite some successful applications of goal-driven navigation, existing deep reinforcement learning (DRL)-based approaches notoriously suffers from poor data efficiency issue. One of the reasons is that the goal information is decoupled…

Robotics · Computer Science 2023-11-09 Wenhui Huang , Yanxin Zhou , Xiangkun He , Chen Lv

Reinforcement learning (RL) algorithms for real-world robotic applications need a data-efficient learning process and the ability to handle complex, unknown dynamical systems. These requirements are handled well by model-based and…

Robotics · Computer Science 2017-06-20 Yevgen Chebotar , Karol Hausman , Marvin Zhang , Gaurav Sukhatme , Stefan Schaal , Sergey Levine