arXiv research

The paper honors Lai's contributions to multi-armed bandits and establishes new regret bounds.

Paper improves regret bounds for Gaussian process upper confidence bound in Bayesian optimization.

A new differentiable UCB algorithm for linear bandits learns adaptive confidence bounds.

The estimation of probabilities of default (PDs) for low default portfolios by means of upper confidence bounds is a well established procedure in many financial institutions. However, there are often discussions within the institutions or between institutions and supervisors about which confidence level to use for the…

This paper improves GP-UCB by using a shifted exponential distribution for confidence parameters.

This note gives a short, self-contained, proof of a sharp connection between Gittins indices and Bayesian upper confidence bound algorithms. I consider a Gaussian multi-armed bandit problem with discount factor $γ$. The Gittins index of an arm is shown to equal the $γ$-quantile of the posterior distribution of the arm'…

Improved Bayesian optimisation method using randomised Gaussian process UCB.

Bayesian methods improve drug discovery experiment design.

One-bit feedback suffices for a bandit problem's optimal strategy.

In this paper, the method UCB-RS, which resorts to recommendation system (RS) for enhancing the upper-confidence bound algorithm UCB, is presented. The proposed method is used for dealing with non-stationary and large-state spaces multi-armed bandit problems. The proposed method has been targeted to the problem of the …

A new method optimizes robustness measures under input uncertainty using randomized Gaussian process upper confidence bound.

This paper analyzes regret bounds for Gaussian process Thompson sampling.

New bounds for Bayesian bandits show prior improves performance.

Upper Confidence Bound (UCB) method is arguably the most celebrated one used in online decision making with partial information feedback. Existing techniques for constructing confidence bounds are typically built upon various concentration inequalities, which thus lead to over-exploration. In this paper, we propose a n…

Bayesian bandit algorithms with approximate inference improve regret bounds in stochastic linear bandits.

Paper proposes a new UCB approach for estimating maximum mean.

New principle optimizes bandit decisions with context.

Confidence measures for the generalization error are crucial when small training samples are used to construct classifiers. A common approach is to estimate the generalization error by resampling and then assume the resampled estimator follows a known distribution to form a confidence set [Kohavi 1995, Martin 1996,Yang…

This paper proposes a DGP approach with UCBs for point target tracking over WSNs.

Upper bound on withdrawal success for geometric Levy alpha-stable wealth process.

EB-TCε identifies the best arm with ε confidence in stochastic bandits.

Study optimizes dynamic product selection and pricing using censored preference feedback.

Paper defines and solves a problem in representation learning to ensure fairness with high confidence.

Designs adaptive controller for networked control systems with wireless data transmission.

This paper is devoted to regret lower bounds in the classical model of stochastic multi-armed bandit. A well-known result of Lai and Robbins, which has then been extended by Burnetas and Katehakis, has established the presence of a logarithmic bound for all consistent policies. We relax the notion of consistence, and e…

EBUCB framework achieves optimal regret with bounded approximate inference error.

Algorithm aggregates rewards from multiple players to learn related tasks in online bandit learning.

A new algorithm for better decision-making in recommendation systems.

UCB algorithm provides stable sample means for sequential data.

A bandit problem with filtered Poisson process data.

We study an extension of the classic stochastic multi-armed bandit problem which involves multiple plays and Markovian rewards in the rested bandits setting. In order to tackle this problem we consider an adaptive allocation rule which at each stage combines the information from the sample means of all the arms, with t…

Paper presents robust confidence sequences for means with known moment bounds and arbitrary corruption.

Bayes-UCBVI tackles reinforcement learning with a new upper confidence bound method.

New algorithm optimizes online decision-making with dynamically generated actions.

I introduce and analyse an anytime version of the Optimally Confident UCB (OCUCB) algorithm designed for minimising the cumulative regret in finite-armed stochastic bandits with subgaussian noise. The new algorithm is simple, intuitive (in hindsight) and comes with the strongest finite-time regret guarantees for a hori…

Contextual bandits are widely used in Internet services from news recommendation to advertising, and to Web search. Generalized linear models (logistical regression in particular) have demonstrated stronger performance than linear models in many applications where rewards are binary. However, most theoretical analyses …

We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the episodes, and both the loss received and the budget consumption are revealed at the e…

New algorithms identify best policies in discounted linear MDPs efficiently.

CRB tackles rising rewards in combinatorial online learning.

GP-UCB performs suboptimally under certain conditions, as shown by a new regret lower bound.

A new UCB algorithm for heavy-tailed bandits with near-optimal regret.

Nonparametric modeling approaches show very promising results in the area of system identification and control. A naturally provided model confidence is highly relevant for system-theoretical considerations to provide guarantees for application scenarios. Gaussian process regression represents one approach which provid…

Improved UCB method for stochastic bandits using distance tuning.

We present two algorithms for Bayesian optimization in the batch feedback setting, based on Gaussian process upper confidence bound and Thompson sampling approaches, along with frequentist regret guarantees and numerical results.

Efficiently identifies good policies by choosing contexts for human feedback.

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 bounds in the inverse reinforcement learning setting---where the true reward fun…

New algorithm reduces regret in linear mixture SSPs without cost bounds.

Algorithm maximizes rewards with a budget and giving up option.