English
Related papers

Related papers: Value-aware Importance Weighting for Off-policy Re…

200 papers

Importance sampling (IS) represents a fundamental technique for a large surge of off-policy reinforcement learning approaches. Policy gradient (PG) methods, in particular, significantly benefit from IS, enabling the effective reuse of…

Machine Learning · Computer Science 2024-05-10 Matteo Papini , Giorgio Manganini , Alberto Maria Metelli , Marcello Restelli

Efficient credit assignment is essential for reinforcement learning algorithms in both prediction and control settings. We describe a unified view on temporal-difference algorithms for selective credit assignment. These selective algorithms…

Machine Learning · Computer Science 2022-02-22 Veronica Chelu , Diana Borsa , Doina Precup , Hado van Hasselt

Recent work on policy learning from observational data has highlighted the importance of efficient policy evaluation and has proposed reductions to weighted (cost-sensitive) classification. But, efficient policy evaluation need not yield…

Machine Learning · Computer Science 2020-02-13 Andrew Bennett , Nathan Kallus

Deep neuroevolution, that is evolutionary policy search methods based on deep neural networks, have recently emerged as a competitor to deep reinforcement learning algorithms due to their better parallelization capabilities. However, these…

Machine Learning · Computer Science 2018-08-20 Aloïs Pourchot , Nicolas Perrin , Olivier Sigaud

Importance sampling is a widely used technique to reduce the variance of a Monte Carlo estimator by an appropriate change of measure. In this work, we study importance sam- pling in the framework of diffusion process and consider the change…

Probability · Mathematics 2018-03-28 Carsten Hartmann , Christof Schütte , Marcus Weber , Wei Zhang

In offline reinforcement learning, a policy needs to be learned from a single pre-collected dataset. Typically, policies are thus regularized during training to behave similarly to the data generating policy, by adding a penalty based on a…

Machine Learning · Computer Science 2021-07-13 Phillip Swazinna , Steffen Udluft , Daniel Hein , Thomas Runkler

Modern off-policy reinforcement learning algorithms often rely on simple uniform replay sampling and it remains unclear when and why non-uniform replay improves over this strong baseline. Across diverse RL settings, we show that the…

Machine Learning · Computer Science 2026-05-19 Michal Korniak , Mikołaj Czarnecki , Yarden As , Piotr Miłoś , Pieter Abbeel , Michal Nauman

In many learning problems, the training and testing data follow different distributions and a particularly common situation is the \textit{covariate shift}. To correct for sampling biases, most approaches, including the popular kernel mean…

Machine Learning · Computer Science 2020-03-13 Henry Lam , Fengpei Li , Siddharth Prusty

Many NLP tasks require to automatically identify the most significant words in a text. In this work, we derive word significance from models trained to solve semantic task: Natural Language Inference and Paraphrase Identification. Using an…

Computation and Language · Computer Science 2023-06-01 Dávid Javorský , Ondřej Bojar , François Yvon

The use of past experiences to accelerate temporal difference (TD) learning of value functions, or experience replay, is a key component in deep reinforcement learning. Prioritization or reweighting of important experiences has shown to…

Artificial Intelligence · Computer Science 2020-06-24 Samarth Sinha , Jiaming Song , Animesh Garg , Stefano Ermon

Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance of these estimators is often high, especially when…

Machine Learning · Computer Science 2021-09-15 Simon P. Shen , Yecheng Jason Ma , Omer Gottesman , Finale Doshi-Velez

We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted rewards approximate the expected return under the…

Machine Learning · Computer Science 2026-05-11 Xiang Li , Nan Jiang

We consider statistical learning problems, when the distribution $P'$ of the training observations $Z'_1,\; \ldots,\; Z'_n$ differs from the distribution $P$ involved in the risk one seeks to minimize (referred to as the test distribution)…

Machine Learning · Statistics 2020-02-20 Robin Vogel , Mastane Achab , Stéphan Clémençon , Charles Tillier

Many sequential decision-making systems leverage data collected using prior policies to propose a new policy. For critical applications, it is important that high-confidence guarantees on the new policy's behavior are provided before…

Machine Learning · Computer Science 2021-01-26 Yash Chandak , Shiv Shankar , Philip S. Thomas

This paper studies off-policy evaluation (OPE) in reinforcement learning with a focus on behavior policy estimation for importance sampling. Prior work has shown empirically that estimating a history-dependent behavior policy can lead to…

Machine Learning · Computer Science 2025-05-29 Hongyi Zhou , Josiah P. Hanna , Jin Zhu , Ying Yang , Chengchun Shi

We present a novel off-policy loss function for learning a transition model in model-based reinforcement learning. Notably, our loss is derived from the off-policy policy evaluation objective with an emphasis on correcting distribution…

Machine Learning · Computer Science 2021-03-04 Cameron Voloshin , Nan Jiang , Yisong Yue

Randomized trials, also known as A/B tests, are used to select between two policies: a control and a treatment. Given a corresponding set of features, we can ideally learn an optimized policy P that maps the A/B test data features to action…

Machine Learning · Computer Science 2018-06-08 Elon Portugaly , Joseph J. Pfeiffer

Feature importance scores are ubiquitous tools for understanding the predictions of machine learning models. However, many popular attribution methods suffer from high instability due to random sampling. Leveraging novel ideas from…

Machine Learning · Statistics 2025-07-08 Jeremy Goldwasser , Giles Hooker

This study presents an importance sampling formulation based on adaptively relaxing parameters from the indicator function and/or the probability density function. The formulation embodies the prevalent mathematical concept of relaxing a…

Applications · Statistics 2024-04-11 Jianhua Xian , Ziqi Wang

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
‹ Prev 1 4 5 6 7 8 10 Next ›