English
Related papers

Related papers: TSEB: More Efficient Thompson Sampling for Policy …

200 papers

Sample-efficient exploration is crucial not only for discovering rewarding experiences but also for adapting to environment changes in a task-agnostic fashion. A principled treatment of the problem of optimal input synthesis for system…

Machine Learning · Computer Science 2019-10-10 Matthias Schultheis , Boris Belousov , Hany Abdulsamad , Jan Peters

In stochastic bandit problems, a Bayesian policy called Thompson sampling (TS) has recently attracted much attention for its excellent empirical performance. However, the theoretical analysis of this policy is difficult and its asymptotic…

Statistics Theory · Mathematics 2013-11-11 Junya Honda , Akimichi Takemura

We study reinforcement learning in stochastic path (SP) problems. The goal in these problems is to maximize the expected sum of rewards until the agent reaches a terminal state. We provide the first regret guarantees in this general problem…

Machine Learning · Computer Science 2022-10-18 Christoph Dann , Chen-Yu Wei , Julian Zimmert

This paper introduces and addresses a wide class of stochastic bandit problems where the function mapping the arm to the corresponding reward exhibits some known structural properties. Most existing structures (e.g. linear, Lipschitz,…

Machine Learning · Statistics 2017-11-02 Richard Combes , Stefan Magureanu , Alexandre Proutiere

We study reinforcement learning (RL) for decision processes with non-Markovian reward, in which high-level knowledge of the task in the form of reward machines is available to the learner. We consider probabilistic reward machines with…

Machine Learning · Computer Science 2024-12-30 Hippolyte Bourel , Anders Jonsson , Odalric-Ambrym Maillard , Chenxiao Ma , Mohammad Sadegh Talebi

We study tabular reinforcement learning problems with multiple steps of lookahead information. Before acting, the learner observes $\ell$ steps of future transition and reward realizations: the exact state the agent would reach and the…

Machine Learning · Computer Science 2026-01-16 Nadav Merlis

Reinforcement learning with human feedback (RLHF), which learns a reward model from human preference data and then optimizes a policy to favor preferred responses, has emerged as a central paradigm for aligning large language models (LLMs)…

Machine Learning · Statistics 2025-09-29 Gen Li , Yuling Yan

Many interventions, such as vaccines in clinical trials or coupons in online marketplaces, must be assigned sequentially without full knowledge of their effects. Multi-armed bandit algorithms have proven successful in such settings.…

Machine Learning · Statistics 2026-05-07 Aidan Gleich , Eric Laber , Alexander Volfovsky

We address the problem of Bayesian reinforcement learning using efficient model-based online planning. We propose an optimism-free Bayes-adaptive algorithm to induce deeper and sparser exploration with a theoretical bound on its performance…

Machine Learning · Computer Science 2020-06-30 Divya Grover , Debabrota Basu , Christos Dimitrakakis

We consider the problem of repeatedly choosing policies to maximize social welfare. Welfare is a weighted sum of private utility and public revenue. Earlier outcomes inform later policies. Utility is not observed, but indirectly inferred.…

Econometrics · Economics 2024-07-30 Nicolo Cesa-Bianchi , Roberto Colomboni , Maximilian Kasy

Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…

Machine Learning · Computer Science 2022-12-01 Alain Andres , Esther Villar-Rodriguez , Javier Del Ser

A contextual bandit is a popular framework for online learning to act under uncertainty. In practice, the number of actions is huge and their expected rewards are correlated. In this work, we introduce a general framework for capturing such…

Machine Learning · Computer Science 2023-03-07 Imad Aouali , Branislav Kveton , Sumeet Katariya

Designing efficient exploration is central to Reinforcement Learning due to the fundamental problem posed by the exploration-exploitation dilemma. Bayesian exploration strategies like Thompson Sampling resolve this trade-off in a principled…

Machine Learning · Computer Science 2021-10-27 Rong Zhu , Mattia Rigotti

We address multi-armed bandits (MAB) where the objective is to maximize the cumulative reward under a probabilistic linear constraint. For a few real-world instances of this problem, constrained extensions of the well-known Thompson…

Machine Learning · Computer Science 2020-05-14 Vidit Saxena , Joseph E. Gonzalez , Joakim Jaldén

In the field of reinforcement learning there has been recent progress towards safety and high-confidence bounds on policy performance. However, to our knowledge, no practical methods exist for determining high-confidence policy performance…

Artificial Intelligence · Computer Science 2018-06-26 Daniel S. Brown , Scott Niekum

We consider the problem of learning an unknown Markov Decision Process (MDP) that is weakly communicating in the infinite horizon setting. We propose a Thompson Sampling-based reinforcement learning algorithm with dynamic episodes (TSDE).…

Machine Learning · Computer Science 2017-09-15 Yi Ouyang , Mukul Gagrani , Ashutosh Nayyar , Rahul Jain

We consider reinforcement learning in parameterized Markov Decision Processes (MDPs), where the parameterization may induce correlation across transition probabilities or rewards. Consequently, observing a particular state transition might…

Machine Learning · Statistics 2015-04-01 Aditya Gopalan , Shie Mannor

We propose a simple model selection approach for algorithms in stochastic bandit and reinforcement learning problems. As opposed to prior work that (implicitly) assumes knowledge of the optimal regret, we only require that each base…

Machine Learning · Computer Science 2020-12-25 Aldo Pacchiano , Christoph Dann , Claudio Gentile , Peter Bartlett

We consider settings where an allocation has to be chosen repeatedly, returns are unknown but can be learned, and decisions are subject to constraints. Our model covers two-sided and one-sided matching, even with complex constraints. We…

Econometrics · Economics 2020-11-05 Maximilian Kasy , Alexander Teytelboym

Psychological research shows that enjoyment of many goods is subject to satiation, with short-term satisfaction declining after repeated exposures to the same item. Nevertheless, proposed algorithms for powering recommender systems seldom…

Machine Learning · Computer Science 2021-10-28 Liu Leqi , Fatma Kilinc-Karzan , Zachary C. Lipton , Alan L. Montgomery