English
Related papers

Related papers: Off-Policy Risk Assessment in Contextual Bandits

200 papers

Many practical applications, such as recommender systems and learning to rank, involve solving multiple similar tasks. One example is learning of recommendation policies for users with similar movie preferences, where the users may still…

Machine Learning · Computer Science 2022-12-12 Joey Hong , Branislav Kveton , Sumeet Katariya , Manzil Zaheer , Mohammad Ghavamzadeh

This work studies the problem of batch off-policy evaluation for Reinforcement Learning in partially observable environments. Off-policy evaluation under partial observability is inherently prone to bias, with risk of arbitrarily large…

Machine Learning · Computer Science 2019-11-26 Guy Tennenholtz , Shie Mannor , Uri Shalit

Off-policy evaluation (OPE) is a critical challenge in robust decision-making that seeks to assess the performance of a new policy using data collected under a different policy. However, the existing OPE methodologies suffer from several…

Machine Learning · Statistics 2025-02-11 Muhammad Faaiz Taufiq

Estimation of importance sampling weights for off-policy evaluation of contextual bandits often results in imbalance - a mismatch between the desired and the actual distribution of state-action pairs after weighting. In this work we present…

Machine Learning · Computer Science 2020-03-06 Arjun Sondhi , David Arbour , Drew Dimmery

Contextual bandit algorithms often estimate reward models to inform decision-making. However, true rewards can contain action-independent redundancies that are not relevant for decision-making. We show it is more data-efficient to estimate…

Machine Learning · Computer Science 2023-02-27 Aldo Gael Carranza , Sanath Kumar Krishnamurthy , Susan Athey

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

We develop a learning principle and an efficient algorithm for batch learning from logged bandit feedback. This learning setting is ubiquitous in online systems (e.g., ad placement, web search, recommendation), where an algorithm makes a…

Machine Learning · Computer Science 2015-05-22 Adith Swaminathan , Thorsten Joachims

In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative evaluation using observational data can help practitioners understand the generalization performance of new policies. However, this type of…

Machine Learning · Computer Science 2023-10-27 Shengpu Tang , Jenna Wiens

Off-policy learning is a framework for optimizing policies without deploying them, using data collected by another policy. In recommender systems, this is especially challenging due to the imbalance in logged data: some items are…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Branislav Kveton , Michal Kompan

We study contextual bandits in the presence of a stage-wise constraint when the constraint must be satisfied both with high probability and in expectation. We start with the linear case where both the reward function and the stage-wise…

Machine Learning · Computer Science 2025-08-22 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett

In this work, we consider the off-policy policy evaluation problem for contextual bandits and finite horizon reinforcement learning in the nonstationary setting. Reusing old data is critical for policy evaluation, but existing estimators…

Machine Learning · Computer Science 2023-02-24 Vincent Liu , Yash Chandak , Philip Thomas , Martha White

We study contextual bandit learning with an abstract policy class and continuous action space. We obtain two qualitatively different regret bounds: one competes with a smoothed version of the policy class under no continuity assumptions,…

Machine Learning · Statistics 2020-06-23 Akshay Krishnamurthy , John Langford , Aleksandrs Slivkins , Chicheng Zhang

In production systems, contextual bandit approaches often rely on direct reward models that take both action and context as input. However, these models can suffer from confounding, making it difficult to isolate the effect of the action…

Machine Learning · Computer Science 2025-09-16 Alexandre Gilotte , Otmane Sakhi , Imad Aouali , Benjamin Heymann

Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…

Machine Learning · Computer Science 2020-08-12 Omer Gottesman , Joseph Futoma , Yao Liu , Sonali Parbhoo , Leo Anthony Celi , Emma Brunskill , Finale Doshi-Velez

Conservative Contextual Bandits (CCBs) address safety in sequential decision making by requiring that an agent's policy, along with minimizing regret, also satisfies a safety constraint: the performance is not worse than a baseline policy…

Machine Learning · Computer Science 2024-12-10 Rohan Deb , Mohammad Ghavamzadeh , Arindam Banerjee

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

Off-policy evaluation estimates how a target policy would perform using data collected by a different behavior policy, which is crucial when online testing is costly or risky, such as in recommendation or healthcare. Standard importance…

Machine Learning · Computer Science 2026-05-29 Ziwen Xie , Shaowen Xiang , Hongyu He , Dianbo Liu

We propose a new framework for designing estimators for off-policy evaluation in contextual bandits. Our approach is based on the asymptotically optimal doubly robust estimator, but we shrink the importance weights to minimize a bound on…

Machine Learning · Computer Science 2020-09-22 Yi Su , Maria Dimakopoulou , Akshay Krishnamurthy , Miroslav Dudík

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data…

This paper deals with optimal policy learning (OPL) with observational data, i.e. data-driven optimal decision-making, in multi-action (or multi-arm) settings, where a finite set of decision options is available. It is organized in three…

Machine Learning · Statistics 2024-04-01 Giovanni Cerulli
‹ Prev 1 3 4 5 6 7 10 Next ›