English
Related papers

Related papers: Thompson Sampling is Asymptotically Optimal in Gen…

200 papers

Thompson sampling has been shown to be an effective policy across a variety of online learning tasks. Many works have analyzed the finite time performance of Thompson sampling, and proved that it achieves a sub-linear regret under a broad…

Machine Learning · Computer Science 2020-11-10 Cem Kalkanli , Ayfer Ozgur

Thompson sampling has proven effective across a wide range of stationary bandit environments. However, as we demonstrate in this paper, it can perform poorly when applied to non-stationary environments. We attribute such failures to the…

Machine Learning · Computer Science 2025-05-06 Yueyang Liu , Xu Kuang , Benjamin Van Roy

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions. The task for an agent is to attain the best possible asymptotic reward where the…

Machine Learning · Computer Science 2007-05-23 Daniil Ryabko , Marcus Hutter

Thompson Sampling is one of the most effective methods for contextual bandits and has been generalized to posterior sampling for certain MDP settings. However, existing posterior sampling methods for reinforcement learning are limited by…

Machine Learning · Computer Science 2022-08-24 Christoph Dann , Mehryar Mohri , Tong Zhang , Julian Zimmert

We use optimism to introduce generic asymptotically optimal reinforcement learning agents. They achieve, with an arbitrary finite or compact class of environments, asymptotically optimal behavior. Furthermore, in the finite deterministic…

Artificial Intelligence · Computer Science 2013-05-17 Peter Sunehag , Marcus Hutter

Thompson sampling is an efficient algorithm for sequential decision making, which exploits the posterior uncertainty to address the exploration-exploitation dilemma. There has been significant recent interest in integrating Bayesian neural…

Machine Learning · Statistics 2020-08-07 Zhendong Wang , Mingyuan Zhou

Contextual multi-armed bandits are classical models in reinforcement learning for sequential decision-making associated with individual information. A widely-used policy for bandits is Thompson Sampling, where samples from a data-driven…

Machine Learning · Statistics 2021-11-30 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Contextual bandits constitute a classical framework for decision-making under uncertainty. In this setting, the goal is to learn the arms of highest reward subject to contextual information, while the unknown reward parameters of each arm…

Machine Learning · Statistics 2024-02-19 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Thompson sampling (TS) is a Bayesian randomized exploration strategy that samples options (e.g., system parameters or control laws) from the current posterior and then applies the selected option that is optimal for a task, thereby…

Machine Learning · Computer Science 2026-02-06 Kaikai Zheng , Dawei Shi , Yang Shi , Long Wang

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

We address the problem of reinforcement learning in which observations may exhibit an arbitrary form of stochastic dependence on past observations and actions, i.e. environments more general than (PO)MDPs. The task for an agent is to attain…

Machine Learning · Computer Science 2009-12-30 Daniil Ryabko , Marcus Hutter

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

Thompson sampling, a Bayesian method for balancing exploration and exploitation in bandit problems, has theoretical guarantees and exhibits strong empirical performance in many domains. Traditional Thompson sampling, however, assumes…

Machine Learning · Computer Science 2018-12-04 Andrew Stirn , Tony Jebara

Stochastic approximation is a powerful class of algorithms with celebrated success. However, a large body of previous analysis focuses on stochastic approximations driven by contractive operators, which is not applicable in some important…

Machine Learning · Computer Science 2025-11-21 Ethan Blaser , Shangtong Zhang

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

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

We aim to efficiently allocate a fixed simulation budget to identify the top-mc designs for each context among a finite number of contexts. The performance of each design under a context is measured by an identifiable statistical…

Methodology · Statistics 2023-07-03 Xinbo Shi , Yijie Peng , Gongbo Zhang

We investigate finite stochastic partial monitoring, which is a general model for sequential learning with limited feedback. While Thompson sampling is one of the most promising algorithms on a variety of online decision-making problems,…

Machine Learning · Statistics 2021-06-11 Taira Tsuchiya , Junya Honda , Masashi Sugiyama

We present a new algorithm for general reinforcement learning where the true environment is known to belong to a finite class of N arbitrary models. The algorithm is shown to be near-optimal for all but O(N log^2 N) time-steps with high…

Machine Learning · Computer Science 2013-08-23 Tor Lattimore , Marcus Hutter , Peter Sunehag

Recently, it has been shown how sampling actions from the predictive distribution over the optimal action-sometimes called Thompson sampling-can be applied to solve sequential adaptive control problems, when the optimal policy is known for…

Artificial Intelligence · Computer Science 2014-09-24 Pedro A. Ortega , Daniel A. Braun
‹ Prev 1 2 3 10 Next ›