English
Related papers

Related papers: Sample Complexity Reduction via Policy Difference …

200 papers

Several researchers have recently investigated the connection between reinforcement learning and classification. We are motivated by proposals of approximate policy iteration schemes without value functions which focus on policy…

Machine Learning · Computer Science 2008-07-06 Christos Dimitrakakis , Michail G. Lagoudakis

We design and implement an adaptive experiment (a ``contextual bandit'') to learn a targeted treatment assignment policy, where the goal is to use a participant's survey responses to determine which charity to expose them to in a donation…

In linear contextual bandits, the objective is to select actions that maximize cumulative rewards, modeled as a linear function with unknown parameters. Although Thompson Sampling performs well empirically, it does not achieve optimal…

Machine Learning · Statistics 2025-06-18 Wonyoung Kim

This paper studies model-based bandit and reinforcement learning (RL) with nonlinear function approximations. We propose to study convergence to approximate local maxima because we show that global convergence is statistically intractable…

Machine Learning · Computer Science 2022-08-04 Kefan Dong , Jiaqi Yang , Tengyu Ma

Contextual bandit problems are a natural fit for many information retrieval tasks, such as learning to rank, text classification, recommendation, etc. However, existing learning methods for contextual bandit problems have one of two…

Information Retrieval · Computer Science 2020-02-06 Rolf Jagerman , Ilya Markov , Maarten de Rijke

We study the problem of experiment planning with function approximation in contextual bandit problems. In settings where there is a significant overhead to deploying adaptive algorithms -- for example, when the execution of the data…

Machine Learning · Computer Science 2024-01-11 Aldo Pacchiano , Jonathan N. Lee , Emma Brunskill

Linear Temporal Logic (LTL) is widely used to specify high-level objectives for system policies, and it is highly desirable for autonomous systems to learn the optimal policy with respect to such specifications. However, learning the…

Machine Learning · Computer Science 2023-10-26 Daqian Shao , Marta Kwiatkowska

Thompson Sampling has been widely used for contextual bandit problems due to the flexibility of its modeling power. However, a general theory for this class of methods in the frequentist setting is still lacking. In this paper, we present a…

Machine Learning · Computer Science 2021-10-05 Tong Zhang

We study how representation learning can improve the learning efficiency of contextual bandit problems. We study the setting where we play T contextual linear bandits with dimension d simultaneously, and these T bandit tasks collectively…

Machine Learning · Computer Science 2025-01-08 Jiabin Lin , Shana Moothedath , Namrata Vaswani

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

Machine Learning · Statistics 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

In this paper, we address the stochastic contextual linear bandit problem, where a decision maker is provided a context (a random set of actions drawn from a distribution). The expected reward of each action is specified by the inner…

Machine Learning · Statistics 2023-05-30 Osama A. Hanna , Lin F. Yang , Christina Fragouli

The performance of reinforcement learning (RL) algorithms is sensitive to the choice of hyperparameters, with the learning rate being particularly influential. RL algorithms fail to reach convergence or demand an extensive number of samples…

Machine Learning · Computer Science 2024-08-09 Aida Afshar , Aldo Pacchiano

We present Residual Policy Learning (RPL): a simple method for improving nondifferentiable policies using model-free deep reinforcement learning. RPL thrives in complex robotic manipulation tasks where good but imperfect controllers are…

Robotics · Computer Science 2019-01-04 Tom Silver , Kelsey Allen , Josh Tenenbaum , Leslie Kaelbling

The exploration-exploitation dilemma in reinforcement learning (RL) is a fundamental challenge to efficient RL algorithms. Existing algorithms for finite state and action discounted RL problems address this by assuming sufficient…

Machine Learning · Computer Science 2025-12-09 Caleb Ju , Guanghui Lan

Offline policy learning is aimed at learning decision-making policies using existing datasets of trajectories without collecting additional data. The primary motivation for using reinforcement learning (RL) instead of supervised learning…

In meta reinforcement learning (meta RL), an agent learns from a set of training tasks how to quickly solve a new task, drawn from the same task distribution. The optimal meta RL policy, a.k.a. the Bayes-optimal behavior, is well defined,…

Machine Learning · Computer Science 2024-04-01 Zohar Rimon , Aviv Tamar , Gilad Adler

In many real-world applications, safety constraints for reinforcement learning (RL) algorithms are either unknown or not explicitly defined. We propose a framework that concurrently learns safety constraints and optimal RL policies in such…

Systems and Control · Electrical Eng. & Systems 2023-05-02 Lunet Yifru , Ali Baheri

We present efficient algorithms for the problem of contextual bandits with i.i.d. covariates, an arbitrary sequence of rewards, and an arbitrary class of policies. Our algorithm BISTRO requires d calls to the empirical risk minimization…

Machine Learning · Computer Science 2016-02-09 Alexander Rakhlin , Karthik Sridharan

Exploration in reinforcement learning (RL) suffers from the curse of dimensionality when the state-action space is large. A common practice is to parameterize the high-dimensional value and policy functions using given features. However…

Machine Learning · Computer Science 2019-06-14 Lin F. Yang , Mengdi Wang

Pure exploration in bandits formalises multiple real-world problems, such as tuning hyper-parameters or conducting user studies to test a set of items, where different safety, resource, and fairness constraints on the decision space…

Machine Learning · Computer Science 2026-02-05 Udvas Das , Debabrota Basu