English
Related papers

Related papers: Universal Off-Policy Evaluation

200 papers

Uncertainty estimation is a key component in any deployed machine learning system. One way to evaluate uncertainty estimation is using "out-of-distribution" (OoD) detection, that is, distinguishing between the training data distribution and…

Machine Learning · Computer Science 2021-12-03 Haiwen Huang , Joost van Amersfoort , Yarin Gal

The principal contribution of this paper is a conceptual framework for off-policy reinforcement learning, based on conditional expectations of importance sampling ratios. This framework yields new perspectives and understanding of existing…

Machine Learning · Computer Science 2020-07-31 Mark Rowland , Anna Harutyunyan , Hado van Hasselt , Diana Borsa , Tom Schaul , Rémi Munos , Will Dabney

The average reward criterion is relatively less studied as most existing works in the Reinforcement Learning literature consider the discounted reward criterion. There are few recent works that present on-policy average reward actor-critic…

Machine Learning · Computer Science 2023-07-20 Naman Saxena , Subhojyoti Khastigir , Shishir Kolathaya , Shalabh Bhatnagar

We study off-policy evaluation (OPE) from multiple logging policies, each generating a dataset of fixed size, i.e., stratified sampling. Previous work noted that in this setting the ordering of the variances of different importance sampling…

Machine Learning · Computer Science 2020-10-22 Nathan Kallus , Yuta Saito , Masatoshi Uehara

In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment.…

Machine Learning · Computer Science 2019-11-26 Alex Irpan , Kanishka Rao , Konstantinos Bousmalis , Chris Harris , Julian Ibarz , Sergey Levine

The counterfactual distribution models the effect of the treatment in the untreated group. While most of the work focuses on the expected values of the treatment effect, one may be interested in the whole counterfactual distribution or…

Machine Learning · Statistics 2022-11-04 Diego Martinez-Taboada , Dino Sejdinovic

Matching users based on mutual preferences is a fundamental aspect of services driven by reciprocal recommendations, such as job search and dating applications. Although A/B tests remain the gold standard for evaluating new policies in…

Machine Learning · Computer Science 2025-07-21 Yudai Hayashi , Shuhei Goda , Yuta Saito

We study the problem of estimating the distribution of the return of a policy using an offline dataset that is not generated from the policy, i.e., distributional offline policy evaluation (OPE). We propose an algorithm called Fitted…

Machine Learning · Computer Science 2024-01-01 Runzhe Wu , Masatoshi Uehara , Wen Sun

We study the problem of offline policy optimization in stochastic contextual bandit problems, where the goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. Rather than making…

Machine Learning · Computer Science 2023-09-28 Germano Gabbianelli , Gergely Neu , Matteo Papini

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

We study off-policy evaluation (OPE) in partially observable environments with complex observations, with the goal of developing estimators whose guarantee avoids exponential dependence on the horizon. While such estimators exist for MDPs…

Machine Learning · Computer Science 2024-10-04 Yuheng Zhang , Nan Jiang

A great variety of off-policy learning algorithms exist in the literature, and new breakthroughs in this area continue to be made, improving theoretical understanding and yielding state-of-the-art reinforcement learning algorithms. In this…

Machine Learning · Computer Science 2020-07-31 Mark Rowland , Will Dabney , Rémi Munos

We consider off-policy evaluation of dynamic treatment rules under sequential ignorability, given an assumption that the underlying system can be modeled as a partially observed Markov decision process (POMDP). We propose an estimator,…

Machine Learning · Computer Science 2023-05-10 Yuchen Hu , Stefan Wager

We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data…

Machine Learning · Computer Science 2022-10-05 Xiang Ji , Minshuo Chen , Mengdi Wang , Tuo Zhao

It is well known that the historical logs are used for evaluating and learning policies in interactive systems, e.g. recommendation, search, and online advertising. Since direct online policy learning usually harms user experiences, it is…

Machine Learning · Statistics 2019-08-06 Li He , Long Xia , Wei Zeng , Zhi-Ming Ma , Yihong Zhao , Dawei Yin

In real-world recommender systems and search engines, optimizing ranking decisions to present a ranked list of relevant items is critical. Off-policy evaluation (OPE) for ranking policies is thus gaining a growing interest because it…

Machine Learning · Statistics 2022-02-04 Haruka Kiyohara , Yuta Saito , Tatsuya Matsuhiro , Yusuke Narita , Nobuyuki Shimizu , Yasuo Yamamoto

We study distributional off-policy evaluation (OPE), of which the goal is to learn the distribution of the return for a target policy using offline data generated by a different policy. The theoretical foundation of many existing work…

Machine Learning · Statistics 2025-03-13 Sungee Hong , Zhengling Qi , Raymond K. W. Wong

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…

Machine Learning · Computer Science 2021-12-24 Brett Daley , Christopher Amato

The expectation value <O> of an arbitrary operator O can be obtained via a universal measuring apparatus that is independent of O, by changing only the data-processing of the outcomes. Such a ``universal detector'' performs a joint…

Quantum Physics · Physics 2007-05-23 G. M. D'Ariano , P. Perinotti , M. F. Sacchi

Monotonic policy improvement and off-policy learning are two main desirable properties for reinforcement learning algorithms. In this paper, by lower bounding the performance difference of two policies, we show that the monotonic policy…

Artificial Intelligence · Computer Science 2017-11-02 Ryo Iwaki , Minoru Asada