English
Related papers

Related papers: Revisiting Bellman Errors for Offline Model Select…

200 papers

The use of pessimism, when reasoning about datasets lacking exhaustive exploration has recently gained prominence in offline reinforcement learning. Despite the robustness it adds to the algorithm, overly pessimistic reasoning can be…

Machine Learning · Computer Science 2023-10-25 Tengyang Xie , Ching-An Cheng , Nan Jiang , Paul Mineiro , Alekh Agarwal

We propose and analyze a reinforcement learning principle that approximates the Bellman equations by enforcing their validity only along an user-defined space of test functions. Focusing on applications to model-free offline RL with…

Machine Learning · Computer Science 2022-10-13 Andrea Zanette , Martin J. Wainwright

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

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

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

Offline model-based optimization (MBO) seeks to discover high-performing designs using only a fixed dataset of past evaluations. Most existing methods rely on learning a surrogate model via regression and implicitly assume that good…

Machine Learning · Computer Science 2026-03-05 Shen-Huan Lyu , Rong-Xi Tan , Ke Xue , Yi-Xiao He , Yu Huang , Qingfu Zhang , Chao Qian

We present a model-based offline reinforcement learning policy performance lower bound that explicitly captures dynamics model misspecification and distribution mismatch and we propose an empirical algorithm for optimal offline policy…

Machine Learning · Computer Science 2023-01-30 Kefan Dong , Yannis Flet-Berliac , Allen Nie , Emma Brunskill

Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a…

Machine Learning · Computer Science 2022-11-15 Shengpu Tang , Felipe Vieira Frujeri , Dipendra Misra , Alex Lamb , John Langford , Paul Mineiro , Sebastian Kochman

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

Off-policy reinforcement learning (RL) using a fixed offline dataset of logged interactions is an important consideration in real world applications. This paper studies offline RL using the DQN replay dataset comprising the entire replay…

Machine Learning · Computer Science 2020-11-25 Rishabh Agarwal , Dale Schuurmans , Mohammad Norouzi

We consider the problem of off-policy evaluation for reinforcement learning, where the goal is to estimate the expected reward of a target policy $\pi$ using offline data collected by running a logging policy $\mu$. Standard…

Machine Learning · Computer Science 2020-07-09 Ming Yin , Yu-Xiang Wang

This paper addresses the problem of policy selection in domains with abundant logged data, but with a restricted interaction budget. Solving this problem would enable safe evaluation and deployment of offline reinforcement learning policies…

We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal…

Machine Learning · Computer Science 2019-04-19 Yao Liu , Omer Gottesman , Aniruddh Raghu , Matthieu Komorowski , Aldo Faisal , Finale Doshi-Velez , Emma Brunskill

Offline optimization is a fundamental challenge in science and engineering, where the goal is to optimize black-box functions using only offline datasets. This setting is particularly relevant when querying the objective function is…

Machine Learning · Computer Science 2026-01-07 Minsu Kim , Jiayao Gu , Ye Yuan , Taeyoung Yun , Zixuan Liu , Yoshua Bengio , Can Chen

Motivated by the success of ensembles for uncertainty estimation in supervised learning, we take a renewed look at how ensembles of $Q$-functions can be leveraged as the primary source of pessimism for offline reinforcement learning (RL).…

Machine Learning · Computer Science 2022-05-30 Seyed Kamyar Seyed Ghasemipour , Shixiang Shane Gu , Ofir Nachum

The goal of off-policy evaluation (OPE) is to evaluate a new policy using historical data obtained via a behavior policy. However, because the contextual bandit algorithm updates the policy based on past observations, the samples are not…

Machine Learning · Computer Science 2020-10-27 Masahiro Kato , Yusuke Kaneko

We consider a linear minimum mean squared error (LMMSE) estimation framework with model mismatch where the assumed model order is smaller than that of the underlying linear system which generates the data used in the estimation process. By…

Signal Processing · Electrical Eng. & Systems 2021-05-26 Martin Hellkvist , Ayça Özçelikkale

Recently, machine learning-based channel estimation has attracted much attention. The performance of machine learning-based estimation has been validated by simulation experiments. However, little attention has been paid to the theoretical…

Signal Processing · Electrical Eng. & Systems 2021-07-15 Kai Mei , Jun Liu , Xiaochen Zhang , Nandana Rajatheva , Jibo Wei

Off-policy evaluation (OPE) in ranking settings with large ranking action spaces, which stems from an increase in both the number of unique actions and length of the ranking, is essential for assessing new recommender policies using only…

Machine Learning · Statistics 2025-06-03 Tatsuki Takahashi , Chihiro Maru , Hiroko Shoji

Reinforcement learning (RL) can be used to learn treatment policies and aid decision making in healthcare. However, given the need for generalization over complex state/action spaces, the incorporation of function approximators (e.g., deep…

Machine Learning · Computer Science 2021-07-26 Shengpu Tang , Jenna Wiens