English
Related papers

Related papers: Free from Bellman Completeness: Trajectory Stitchi…

200 papers

Policy-based methods currently dominate reinforcement learning (RL) pipelines for large language model (LLM) reasoning, leaving value-based approaches largely unexplored. We revisit the classical paradigm of Bellman Residual Minimization…

Machine Learning · Computer Science 2025-11-13 Yurun Yuan , Fan Chen , Zeyu Jia , Alexander Rakhlin , Tengyang Xie

In temporal difference (TD) learning, off-policy sampling is known to be more practical than on-policy sampling, and by decoupling learning from data collection, it enables data reuse. It is known that policy evaluation (including…

Machine Learning · Computer Science 2021-06-25 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

We consider off-policy temporal-difference (TD) learning in discounted Markov decision processes, where the goal is to evaluate a policy in a model-free way by using observations of a state process generated without executing the policy. To…

Machine Learning · Computer Science 2018-11-27 Huizhen Yu , A. Rupam Mahmood , Richard S. Sutton

We consider offline reinforcement learning (RL) in $H$-horizon Markov decision processes (MDPs) under the linear $q^\pi$-realizability assumption, where the action-value function of every policy is linear with respect to a given…

Machine Learning · Computer Science 2024-05-28 Volodymyr Tkachuk , Gellért Weisz , Csaba Szepesvári

Given a training dataset, the goal of dataset distillation is to derive a synthetic dataset such that models trained on the latter perform as well as those trained on the training dataset. In this work, we develop and analyze an efficient…

Machine Learning · Computer Science 2025-12-02 Aaryan Gupta , Rishi Saket , Aravindan Raghuveer

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

Machine Learning · Computer Science 2025-04-21 Han-Dong Lim , Donghwan Lee

We study off-dynamics Reinforcement Learning (RL), where the policy is trained on a source domain and deployed to a distinct target domain. We aim to solve this problem via online distributionally robust Markov decision processes (DRMDPs),…

Machine Learning · Computer Science 2024-02-26 Zhishuai Liu , Pan Xu

In many real-world settings, reinforcement learning systems suffer performance degradation when the environment encountered at deployment differs from that observed during training. Distributionally robust reinforcement learning (DR-RL)…

Machine Learning · Computer Science 2026-03-05 Debamita Ghosh , George K. Atia , Yue Wang

Sequential decision making algorithms often struggle to leverage different sources of unstructured offline interaction data. Imitation learning (IL) methods based on supervised learning are robust, but require optimal demonstrations, which…

Machine Learning · Computer Science 2023-04-28 Joey Hejna , Jensen Gao , Dorsa Sadigh

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning…

We study representation learning for Offline Reinforcement Learning (RL), focusing on the important task of Offline Policy Evaluation (OPE). Recent work shows that, in contrast to supervised learning, realizability of the Q-function is not…

Machine Learning · Computer Science 2022-07-14 Jonathan D. Chang , Kaiwen Wang , Nathan Kallus , Wen Sun

A key barrier to using reinforcement learning (RL) in many real-world applications is the requirement of a large number of system interactions to learn a good control policy. Off-policy and Offline RL methods have been proposed to reduce…

Machine Learning · Computer Science 2022-12-02 Wenqi Cui , Linbin Huang , Weiwei Yang , Baosen Zhang

Many AI problems, in robotics and other domains, are goal-based, essentially seeking trajectories leading to various goal states. Reinforcement learning (RL), building on Bellman's optimality equation, naturally optimizes for a single goal,…

Artificial Intelligence · Computer Science 2020-12-22 Tom Jurgenson , Or Avner , Edward Groshev , Aviv Tamar

Offline reinforcement learning (RL) has progressed with return-conditioned supervised learning (RCSL), but its lack of stitching ability remains a limitation. We introduce $Q$-Aided Conditional Supervised Learning (QCS), which effectively…

Machine Learning · Computer Science 2026-03-16 Jeonghye Kim , Suyoung Lee , Woojun Kim , Youngchul Sung

We study offline off-dynamics reinforcement learning (RL) to utilize data from an easily accessible source domain to enhance policy learning in a target domain with limited data. Our approach centers on return-conditioned supervised…

Machine Learning · Computer Science 2026-03-03 Ruhan Wang , Yu Yang , Zhishuai Liu , Dongruo Zhou , Pan Xu

Offline Goal-Conditioned Reinforcement Learning (Offline GCRL) is an important problem in RL that focuses on acquiring diverse goal-oriented skills solely from pre-collected behavior datasets. In this setting, the reward feedback is…

Artificial Intelligence · Computer Science 2024-02-13 Sungyoon Kim , Yunseon Choi , Daiki E. Matsunaga , Kee-Eung Kim

Offline reinforcement learning (RL) algorithms are applied to learn performant, well-generalizing policies when provided with a static dataset of interactions. Many recent approaches to offline RL have seen substantial success, but with one…

Machine Learning · Computer Science 2024-07-30 Padmanaba Srinivasan , William Knottenbelt

Recent works have shown that tackling offline reinforcement learning (RL) with a conditional policy produces promising results. The Decision Transformer (DT) combines the conditional policy approach and a transformer architecture, showing…

Machine Learning · Computer Science 2023-05-26 Taku Yamagata , Ahmed Khalil , Raul Santos-Rodriguez

We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it. We address this problem by extending the framework of robust MDPs to the…

Machine Learning · Computer Science 2017-11-10 Aurko Roy , Huan Xu , Sebastian Pokutta

An off policy reinforcement learning based control strategy is developed for the optimal tracking control problem to achieve the prescribed performance of full states during the learning process. The optimal tracking control problem is…

Systems and Control · Electrical Eng. & Systems 2020-09-02 C. Li , Y. Wang , F. Liu , M. Buss