English
Related papers

Related papers: Consistent On-Line Off-Policy Evaluation

200 papers

Temporal-Difference (TD) learning methods, such as Q-Learning, have proven effective at learning a policy to perform control tasks. One issue with methods like Q-Learning is that the value update introduces bias when predicting the TD…

Machine Learning · Computer Science 2021-10-29 Litian Liang , Yaosheng Xu , Stephen McAleer , Dailin Hu , Alexander Ihler , Pieter Abbeel , Roy Fox

Evaluating and optimizing policies in the presence of unobserved confounders is a problem of growing interest in offline reinforcement learning. Using conventional methods for offline RL in the presence of confounding can not only lead to…

Machine Learning · Statistics 2023-11-08 Chinmaya Kausik , Yangyi Lu , Kevin Tan , Maggie Makar , Yixin Wang , Ambuj Tewari

On-policy distillation (OPD) has become a core technique in the post-training of large language models, yet its training dynamics remain poorly understood. This paper provides a systematic investigation of OPD dynamics and mechanisms. We…

Machine Learning · Computer Science 2026-04-16 Yaxuan Li , Yuxin Zuo , Bingxiang He , Jinqian Zhang , Chaojun Xiao , Cheng Qian , Tianyu Yu , Huan-ang Gao , Wenkai Yang , Zhiyuan Liu , Ning Ding

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…

Machine Learning · Computer Science 2023-09-27 Baturay Saglam , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat

Reinforcement learning (RL) is one of the most vibrant research frontiers in machine learning and has been recently applied to solve a number of challenging problems. In this paper, we primarily focus on off-policy evaluation (OPE), one of…

Machine Learning · Statistics 2022-12-14 Masatoshi Uehara , Chengchun Shi , Nathan Kallus

Due to the inability to interact with the environment, offline reinforcement learning (RL) methods face the challenge of estimating the Out-of-Distribution (OOD) points. Existing methods for addressing this issue either control policy to…

Machine Learning · Computer Science 2024-03-06 Jing Zhang , Chi Zhang , Wenjia Wang , Bing-Yi Jing

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…

Machine Learning · Computer Science 2022-02-03 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

We consider off-policy evaluation (OPE), which evaluates the performance of a new policy from observed data collected from previous experiments, without requiring the execution of the new policy. This finds important applications in areas…

Machine Learning · Computer Science 2020-08-18 Yihao Feng , Tongzheng Ren , Ziyang Tang , Qiang Liu

Off-policy evaluation (OPE) is widely applied in sectors such as pharmaceuticals and e-commerce to evaluate the efficacy of novel products or policies from offline datasets. This paper introduces a causal deepset framework that relaxes…

Machine Learning · Statistics 2024-07-26 Runpeng Dai , Jianing Wang , Fan Zhou , Shikai Luo , Zhiwei Qin , Chengchun Shi , Hongtu Zhu

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky

Off-policy evaluation is critical in a number of applications where new policies need to be evaluated offline before online deployment. Most existing methods focus on the expected return, define the target parameter through averaging and…

Machine Learning · Statistics 2023-02-10 Yingying Zhang , Chengchun Shi , Shikai Luo

This paper proposes a data-driven method for learning convergent control policies from offline data using Contraction theory. Contraction theory enables constructing a policy that makes the closed-loop system trajectories inherently…

Machine Learning · Computer Science 2022-02-04 Navid Rezazadeh , Maxwell Kolarich , Solmaz S. Kia , Negar Mehr

In this paper, we present two effective policy learning algorithms for multi-agent online coordination(MA-OC) problem. The first one, \texttt{MA-SPL}, not only can achieve the optimal $(1-\frac{c}{e})$-approximation guarantee for the MA-OC…

Multiagent Systems · Computer Science 2025-09-29 Qixin Zhang , Yan Sun , Can Jin , Xikun Zhang , Yao Shu , Puning Zhao , Li Shen , Dacheng Tao

One of the main obstacles to broad application of reinforcement learning methods is the parameter sensitivity of our core learning algorithms. In many large-scale applications, online computation and function approximation represent key…

Artificial Intelligence · Computer Science 2016-10-25 Martha White , Adam White

On-policy distillation (OPD) and on-policy self-distillation (OPSD) have emerged as promising post-training methods for large language models, offering dense token-level supervision on trajectories sampled from the model's own policy.…

Artificial Intelligence · Computer Science 2026-05-26 Siqi Zhu , Xuyan Ye , Hongyu Lu , Weiye Shi , Ge Liu

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

We consider off-policy policy evaluation with function approximation (FA) in average-reward MDPs, where the goal is to estimate both the reward rate and the differential value function. For this problem, bootstrapping is necessary and,…

Machine Learning · Computer Science 2022-10-19 Shangtong Zhang , Yi Wan , Richard S. Sutton , Shimon Whiteson

Off-policy evaluation (OPE) estimates the value of a contextual bandit policy prior to deployment. As such, OPE plays a critical role in ensuring safety in high-stakes domains such as healthcare. However, standard OPE approaches are limited…

Machine Learning · Computer Science 2025-11-25 Aishwarya Mandyam , Kalyani Limaye , Barbara E. Engelhardt , Emily Alsentzer

We study the problem of off-policy critic evaluation in several variants of value-based off-policy actor-critic algorithms. Off-policy actor-critic algorithms require an off-policy critic evaluation step, to estimate the value of the new…

Machine Learning · Computer Science 2019-12-12 Riashat Islam , Raihan Seraj , Samin Yeasar Arnob , Doina Precup

Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) -- the problem of evaluating a new policy using the historical data…

Machine Learning · Computer Science 2020-04-02 Tengyang Xie , Yifei Ma , Yu-Xiang Wang