English
Related papers

Related papers: More Efficient Randomized Exploration for Reinforc…

200 papers

In this paper, we introduce and analyze a variant of the Thompson sampling (TS) algorithm for contextual bandits. At each round, traditional TS requires samples from the current posterior distribution, which is usually intractable. To…

Machine Learning · Statistics 2024-07-23 Pierre Clavier , Tom Huix , Alain Durmus

Motivated by the pressing need for efficient optimization in online recommender systems, we revisit the cascading bandit model proposed by Kveton et al. (2015). While Thompson sampling (TS) algorithms have been shown to be empirically…

Machine Learning · Computer Science 2021-05-18 Zixin Zhong , Wang Chi Cheung , Vincent Y. F. Tan

Reinforcement Learning (RL) has gained substantial attention across diverse application domains and theoretical investigations. Existing literature on RL theory largely focuses on risk-neutral settings where the decision-maker learns to…

Machine Learning · Computer Science 2024-12-24 Zhengqi Wu , Renyuan Xu

We consider incentivized exploration: a version of multi-armed bandits where the choice of arms is controlled by self-interested agents, and the algorithm can only issue recommendations. The algorithm controls the flow of information, and…

Computer Science and Game Theory · Computer Science 2022-06-14 Mark Sellke , Aleksandrs Slivkins

Exploration in multi-task reinforcement learning is critical in training agents to deduce the underlying MDP. Many of the existing exploration frameworks such as $E^3$, $R_{max}$, Thompson sampling assume a single stationary MDP and are not…

Artificial Intelligence · Computer Science 2016-12-04 Sai Praveen Bangaru , JS Suhas , Balaraman Ravindran

Learning complex robot behavior through interactions with the environment necessitates principled exploration. Effective strategies should prioritize exploring regions of the state-action space that maximize rewards, with optimistic…

Machine Learning · Computer Science 2025-03-12 Jasmine Bayrooti , Carl Henrik Ek , Amanda Prorok

We develop a model selection approach to tackle reinforcement learning with adversarial corruption in both transition and reward. For finite-horizon tabular MDPs, without prior knowledge on the total amount of corruption, our algorithm…

Machine Learning · Computer Science 2024-12-31 Chen-Yu Wei , Christoph Dann , Julian Zimmert

Cold-start exploration is a core challenge in large-scale recommender systems: new or data-sparse items must receive traffic to estimate value, but over-exploration harms users and wastes impressions. In practice, Thompson Sampling (TS) is…

Machine Learning · Computer Science 2026-02-03 Zhenyu Zhao , David Zhang , Ellie Zhao , Ehsan Saberian

We propose an extension of Thompson sampling to optimization problems over function spaces where the objective is a known functional of an unknown operator's output. We assume that queries to the operator (such as running a high-fidelity…

Machine Learning · Statistics 2026-01-21 Rafael Oliveira , Xuesong Wang , Kian Ming A. Chai , Edwin V. Bonilla

This paper proposes regenerative particle Thompson sampling (RPTS), a flexible variation of Thompson sampling. Thompson sampling itself is a Bayesian heuristic for solving stochastic bandit problems, but it is hard to implement in practice…

Machine Learning · Computer Science 2024-01-24 Zeyu Zhou , Bruce Hajek , Nakjung Choi , Anwar Walid

We present a novel extension of Thompson Sampling for stochastic sequential decision problems with graph feedback, even when the graph structure itself is unknown and/or changing. We provide theoretical guarantees on the Bayesian regret of…

Machine Learning · Computer Science 2017-01-17 Aristide C. Y. Tossou , Christos Dimitrakakis , Devdatt Dubhashi

For the problem of task-agnostic reinforcement learning (RL), an agent first collects samples from an unknown environment without the supervision of reward signals, then is revealed with a reward and is asked to compute a corresponding…

Machine Learning · Computer Science 2022-03-16 Jingfeng Wu , Vladimir Braverman , Lin F. Yang

We study the constrained reinforcement learning problem, in which an agent aims to maximize the expected cumulative reward subject to a constraint on the expected total value of a utility function. In contrast to existing model-based…

Machine Learning · Computer Science 2023-01-10 Arnob Ghosh , Xingyu Zhou , Ness Shroff

This paper proposes a novel method that incorporates empowerment when reasoning actions in reinforcement learning (RL), thereby achieving the flexibility of exploration-exploitation dilemma (EED). In previous methods, empowerment for…

Machine Learning · Computer Science 2026-04-20 Taisuke Kobayashi

Reinforcement learning algorithms typically consider discrete-time dynamics, even though the underlying systems are often continuous in time. In this paper, we introduce a model-based reinforcement learning algorithm that represents…

Machine Learning · Computer Science 2023-11-01 Lenart Treven , Jonas Hübotter , Bhavya Sukhija , Florian Dörfler , Andreas Krause

Practitioners conducting adaptive experiments often encounter two competing priorities: maximizing total welfare (or `reward') through effective treatment assignment and swiftly concluding experiments to implement population-wide…

Machine Learning · Computer Science 2024-07-31 Chao Qin , Daniel Russo

We study the Combinatorial Thompson Sampling policy (CTS) for combinatorial multi-armed bandit problems (CMAB), within an approximation regret setting. Although CTS has attracted a lot of interest, it has a drawback that other usual CMAB…

Machine Learning · Statistics 2023-02-23 Pierre Perrault

Preference feedback, in the form of pairwise comparisons rather than scalar scores, has seen increasing use in applications such as human-, laboratory-, and expert-in-the-loop design, as well as scientific discovery. We propose a Thompson…

Machine Learning · Statistics 2026-04-29 Joseph Lazzaro , Davide Buffelli , Da-shan Shiu , Sattar Vakili

Training models to effectively use test-time compute is crucial for improving the reasoning performance of LLMs. Current methods mostly do so via fine-tuning on search traces or running RL with 0/1 outcome reward, but do these approaches…

Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL). State-of-the-art RL algorithms suffer from high sample complexity, particularly in the sparse reward case, where they can do no better than to…

Machine Learning · Computer Science 2020-01-22 Philippe Morere , Gilad Francis , Tom Blau , Fabio Ramos