English
Related papers

Related papers: Off-Policy Evaluation from Logged Human Feedback

200 papers

The Off-Policy Evaluation (OPE) problem consists of evaluating the performance of counterfactual policies with data collected by another one. To solve the OPE problem, we resort to estimators, which aim to estimate in the most accurate way…

Machine Learning · Computer Science 2024-11-12 Nicolò Felicioni , Michael Benigni , Maurizio Ferrari Dacrema

Learning of preference models from human feedback has been central to recent advances in artificial intelligence. Motivated by the cost of obtaining high-quality human annotations, we study efficient human preference elicitation for…

Machine Learning · Computer Science 2026-02-17 Subhojyoti Mukherjee , Anusha Lalitha , Kousha Kalantari , Aniket Deshmukh , Ge Liu , Yifei Ma , Branislav Kveton

We study the problem of off-policy evaluation (OPE) in Reinforcement Learning (RL), where the aim is to estimate the performance of a new policy given historical data that may have been generated by a different policy, or policies. In…

Machine Learning · Computer Science 2019-12-16 Aurélien F. Bibaut , Ivana Malenica , Nikos Vlassis , Mark J. van der Laan

Developing accurate off-policy estimators is crucial for both evaluating and optimizing for new policies. The main challenge in off-policy estimation is the distribution shift between the logging policy that generates data and the target…

Machine Learning · Computer Science 2023-10-25 Noveen Sachdeva , Lequn Wang , Dawen Liang , Nathan Kallus , Julian McAuley

Human feedback is increasingly used to steer the behaviours of Large Language Models (LLMs). However, it is unclear how to collect and incorporate feedback in a way that is efficient, effective and unbiased, especially for highly subjective…

Computation and Language · Computer Science 2023-10-12 Hannah Rose Kirk , Andrew M. Bean , Bertie Vidgen , Paul Röttger , Scott A. Hale

Off-policy evaluation (OPE) is important for closing the gap between offline training and evaluation of reinforcement learning (RL), by estimating performance and/or rank of target (evaluation) policies using offline trajectories only. It…

Machine Learning · Computer Science 2023-10-17 Qitong Gao , Ge Gao , Juncheng Dong , Vahid Tarokh , Min Chi , Miroslav Pajic

We consider a personalized pricing problem in which we have data consisting of feature information, historical pricing decisions, and binary realized demand. The goal is to perform off-policy evaluation for a new personalized pricing policy…

Machine Learning · Statistics 2023-02-27 Adam N. Elmachtoub , Vishal Gupta , Yunfan Zhao

Recent advances in Large Language Models (LLMs) have spurred interest in designing LLM-based agents for tasks that involve interaction with human and artificial agents. This paper addresses a key aspect in the design of such agents:…

Machine Learning · Computer Science 2025-10-28 Eilam Shapira , Omer Madmon , Reut Apel , Moshe Tennenholtz , Roi Reichart

Off-policy learning in dynamic decision problems is essential for providing strong evidence that a new policy is better than the one in use. But how can we prove superiority without testing the new policy? To answer this question, we…

Machine Learning · Statistics 2015-02-12 Assaf Hallak , François Schnitzler , Timothy Mann , Shie Mannor

Off-policy evaluation is a key component of reinforcement learning which evaluates a target policy with offline data collected from behavior policies. It is a crucial step towards safe reinforcement learning and has been used in…

Machine Learning · Computer Science 2020-12-01 Jinlin Lai , Lixin Zou , Jiaxing Song

Off-policy evaluation methods are important in recommendation systems and search engines, where data collected under an existing logging policy is used to estimate the performance of a new proposed policy. A common approach to this problem…

Machine Learning · Computer Science 2023-01-04 Jaron J. R. Lee , David Arbour , Georgios Theocharous

Unbiased recommender learning (URL) and off-policy evaluation/learning (OPE/L) techniques are effective in addressing the data bias caused by display position and logging policies, thereby consistently improving the performance of…

Machine Learning · Statistics 2025-02-14 Tatsuki Takahashi , Chihiro Maru , Hiroko Shoji

Off-policy learning, referring to the procedure of policy optimization with access only to logged feedback data, has shown importance in various real-world applications, such as search engines, recommender systems, and etc. While the…

Machine Learning · Computer Science 2023-09-28 Xiaoying Zhang , Junpu Chen , Hongning Wang , Hong Xie , Yang Liu , John C. S. Lui , Hang Li

We consider the problem of evaluating the performance of a decision policy using past observational data. The outcome of a policy is measured in terms of a loss (aka. disutility or negative reward) and the main problem is making valid…

Machine Learning · Statistics 2023-07-03 Sofia Ek , Dave Zachariah , Fredrik D. Johansson , Petre Stoica

Reliable automatic evaluation of dialogue systems under an interactive environment has long been overdue. An ideal environment for evaluating dialog systems, also known as the Turing test, needs to involve human interaction, which is…

Computation and Language · Computer Science 2021-09-23 Haoming Jiang , Bo Dai , Mengjiao Yang , Tuo Zhao , Wei Wei

We consider the problem of off-policy evaluation in Markov decision processes. Off-policy evaluation is the task of evaluating the expected return of one policy with data generated by a different, behavior policy. Importance sampling is a…

Machine Learning · Computer Science 2019-05-13 Josiah P. Hanna , Scott Niekum , Peter Stone

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

We study estimator selection and hyper-parameter tuning in off-policy evaluation. Although cross-validation is the most popular method for model selection in supervised learning, off-policy evaluation relies mostly on theory, which provides…

Machine Learning · Computer Science 2024-12-23 Matej Cief , Branislav Kveton , Michal Kompan

There has been a growing interest in off-policy evaluation in the literature such as recommender systems and personalized medicine. We have so far seen significant progress in developing estimators aimed at accurately estimating the…

Machine Learning · Computer Science 2024-04-24 Yuta Saito , Masahiro Nomura

We develop an off-policy actor-critic algorithm for learning an optimal policy from a training set composed of data from multiple individuals. This algorithm is developed with a view towards its use in mobile health.

Machine Learning · Statistics 2016-07-19 S. A. Murphy , Y. Deng , E. B. Laber , H. R. Maei , R. S. Sutton , K. Witkiewitz