English
Related papers

Related papers: STITCH-OPE: Trajectory Stitching with Guided Diffu…

200 papers

Off-dynamics offline reinforcement learning seeks to learn a target-domain policy from a large source dataset and a limited target dataset under mismatched transition dynamics. Existing approaches such as reward augmentation and data…

Machine Learning · Computer Science 2026-05-26 Yu Yang , Yihong Guo , Anqi Liu , Pan Xu

We propose a robust regression approach to off-policy evaluation (OPE) for contextual bandits. We frame OPE as a covariate-shift problem and leverage modern robust regression tools. Ours is a general approach that can be used to augment any…

Machine Learning · Computer Science 2019-11-19 Anqi Liu , Hao Liu , Anima Anandkumar , Yisong Yue

This work focuses on off-policy evaluation (OPE) with function approximation in infinite-horizon undiscounted Markov decision processes (MDPs). For MDPs that are ergodic and linear (i.e. where rewards and dynamics are linear in some known…

Machine Learning · Computer Science 2020-06-24 Nevena Lazic , Dong Yin , Mehrdad Farajtabar , Nir Levine , Dilan Gorur , Chris Harris , Dale Schuurmans

Off-Policy Evaluation (OPE) serves as one of the cornerstones in Reinforcement Learning (RL). Fitted Q Evaluation (FQE) with various function approximators, especially deep neural networks, has gained practical success. While statistical…

Machine Learning · Statistics 2022-02-11 Ruiqi Zhang , Xuezhou Zhang , Chengzhuo Ni , Mengdi Wang

In robotics, diffusion models can capture multi-modal trajectories from demonstrations, making them a transformative approach in imitation learning. However, achieving optimal performance following this regiment requires a large-scale…

Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented trajectories present challenges for reward propagation, resulting in inaccurate…

Machine Learning · Computer Science 2025-12-17 Hang Yu , Di Zhang , Qiwei Du , Yanping Zhao , Hai Zhang , Guang Chen , Eduardo E. Veas , Junqiao Zhao

We consider evaluating and training a new policy for the evaluation data by using the historical data obtained from a different policy. The goal of off-policy evaluation (OPE) is to estimate the expected reward of a new policy over the…

Machine Learning · Statistics 2020-10-19 Masahiro Kato , Masatoshi Uehara , Shota Yasui

On-policy distillation (OPD) has emerged as an efficient post-training paradigm for large language models. However, existing studies largely attribute this advantage to denser and more stable supervision, while the parameter-level…

Computation and Language · Computer Science 2026-05-22 Yuchen Cai , Ding Cao , Liang Lin , Chunxi Luo , Xin Xu , Kai Yang , Weijie Liu , Saiyong Yang , Tianxiang Zhao , Guangzhong Sun , Guiquan Liu , Junfeng Fang

We study the novel problem of future off-policy evaluation (F-OPE) and learning (F-OPL) for estimating and optimizing the future value of policies in non-stationary environments, where distributions vary over time. In e-commerce…

Machine Learning · Computer Science 2025-06-26 Tatsuhiro Shimizu , Kazuki Kawamura , Takanori Muroi , Yusuke Narita , Kei Tateno , Takuma Udagawa , Yuta Saito

Diffusion policies, widely adopted in decision-making scenarios such as robotics, gaming and autonomous driving, are capable of learning diverse skills from demonstration data due to their high representation power. However, the sub-optimal…

Machine Learning · Computer Science 2025-09-30 Ningyuan Yang , Jiaxuan Gao , Feng Gao , Yi Wu , Chao Yu

We consider off-policy policy evaluation when the trajectory data are generated by multiple behavior policies. Recent work has shown the key role played by the state or state-action stationary distribution corrections in the infinite…

Machine Learning · Computer Science 2019-10-14 Xinyun Chen , Lu Wang , Yizhe Hang , Heng Ge , Hongyuan Zha

In this paper, we propose a novel $K$-nearest neighbor resampling procedure for estimating the performance of a policy from historical data containing realized episodes of a decision process generated under a different policy. We provide…

Machine Learning · Statistics 2024-01-11 Michael Giegrich , Roel Oomen , Christoph Reisinger

We consider off-policy evaluation (OPE) of deterministic target policies for reinforcement learning (RL) in environments with continuous action spaces. While it is common to use importance sampling for OPE, it suffers from high variance…

Machine Learning · Computer Science 2024-05-30 Haanvid Lee , Tri Wahyu Guntara , Jongmin Lee , Yung-Kyun Noh , Kee-Eung Kim

Off-Policy Estimation (OPE) methods allow us to learn and evaluate decision-making policies from logged data. This makes them an attractive choice for the offline evaluation of recommender systems, and several recent works have reported…

Machine Learning · Computer Science 2023-09-11 Olivier Jeunen , Ben London

Off-policy evaluation learns a target policy's value with a historical dataset generated by a different behavior policy. In addition to a point estimate, many applications would benefit significantly from having a confidence interval (CI)…

Machine Learning · Statistics 2021-06-09 Chengchun Shi , Runzhe Wan , Victor Chernozhukov , Rui Song

In a sequential decision-making problem, off-policy evaluation estimates the expected cumulative reward of a target policy using logged trajectory data generated from a different behavior policy, without execution of the target policy.…

Machine Learning · Computer Science 2022-11-04 Jie Wang , Rui Gao , Hongyuan Zha

In offline-to-online reinforcement learning (O2O-RL), policies are first safely trained offline using previously collected datasets and then further fine-tuned for tasks via limited online interactions. In a typical O2O-RL pipeline,…

Machine Learning · Computer Science 2026-05-07 Alper Kamil Bozkurt , Xiaoan Xu , Shangtong Zhang , Miroslav Pajic , Yuichi Motai

Generative model-based policies have shown strong performance in imitation-based robotic manipulation by learning action distributions from demonstrations. However, in long-horizon tasks, visually similar observations often recur across…

Robotics · Computer Science 2026-02-10 Yuxuan Hu , Xiangyu Chen , Chuhao Zhou , Yuxi Liu , Gen Li , Jindou Jia , Jianfei Yang

Off-policy evaluation (OPE) methods allow us to compute the expected reward of a policy by using the logged data collected by a different policy. OPE is a viable alternative to running expensive online A/B tests: it can speed up the…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Jacek Golebiowski , Philipp Schmidt , Ziawasch Abedjan , Artur Bekasov

Counterfactual estimators are critical for learning and refining policies using logged data, a process known as Off-Policy Evaluation (OPE). OPE allows researchers to assess new policies without costly experiments, speeding up the…

Artificial Intelligence · Computer Science 2025-01-10 Ritam Guha , Nilavra Pathak
‹ Prev 1 3 4 5 6 7 10 Next ›