New findings show many popular bandit algorithms are unstable, contradicting minimax optimality.
problem Challenges in statistical inference from bandit algorithms due to adaptive, non-i.i.d. nature.
method Analysis of stability properties of optimism-based bandit algorithms.
result Widely used minimax-optimal UCB-style algorithms are unstable.
BaNk-UCB tackles batched nonparametric bandits with k-NN regression and UCB.
problem Sequential decision-making with limited online feedback in domains like medicine and marketing.
method Combines k-NN regression with UCB principle for fully nonparametric, adaptive, and simple implementation.
result Near-optimal regret guarantees under Lipschitz smoothness and margin assumptions, with minimax-optimal rates.
New principle optimizes bandit decisions with context.
problem Dealing with general function classes and large context spaces in bandits.
method Upper Counterfactual Confidence Bounds (UCCB) principle.
result Proves optimality and efficiency in complex settings.
We consider a variant of the classic multi-armed bandit problem where the expected reward of each arm is a function of an unknown parameter. The arms are divided into different groups, each of which has a common parameter. Therefore, when the player selects an arm at each time slot, information of other arms in the sam…
Improved control approach for correlated bandits with better performance.
problem General multi-armed bandit problem with correlated elements.
method Introducing entropy regularisation to obtain a smooth asymptotic approximation of the value function, leading to a semi-index approximation of the optimal decision process.
result Performance of Asymptotic Randomised Control (ARC) algorithm compares favorably with other approaches.
New algorithm explores reinforcement learning with noisy data.
problem Exploration in reinforcement learning with complex value functions.
method Randomized exploration with i.i.d. scalar noises and optimistic reward sampling.
result Achieves worst-case regret bound of O ~ ( p o l y ( d E H ) T ) \widetilde{O}(\mathrm{poly}(d_EH)\sqrt{T}) O ( poly ( d E H ) T ) . UCB-TQL learns from multiple tasks with shared dynamics and adapts to task-specific variations.
problem Transfer reinforcement learning with composite MDPs where tasks share core dynamics but have sparse differences.
method UCB-TQL, a novel transfer RL algorithm for composite MDPs.
result Achieved a regret bound of i l d e O ( e H 5 N ) ilde{O}(\sqrt{eH^5N}) i l d e O ( e H 5 N ) that scales independently of the ambient dimension. Latent variable models improve RL by facilitating efficient learning and exploration.
problem Improving sample efficiency in reinforcement learning.
method Representation view of latent variable models for state-action value functions, incorporating kernel embeddings and UCB exploration.
result Established sample complexity of the proposed approach in online and offline settings, demonstrated superior performance in benchmarks.
A new algorithm for better decision-making in recommendation systems.
problem Stochastic multi-armed bandit problem and cold start problem in recommender systems.
method Proposes Hellinger-UCB, a variant of UCB algorithm using squared Hellinger distance.
result Hellinger-UCB reaches the theoretical lower bound and outperforms other algorithms in practical applications.
UCB-V algorithm improves on UCB for MAB problems with variance estimates.
problem Optimizing arm selection in MAB problems with variance information.
method Asymptotic and high probability analysis of UCB-V algorithm.
result UCB-V can exhibit instability in arm-pulling rates but achieves refined regret bounds.
Optimal policy for multi-armed multi-action bandits with unknown parameters.
problem Optimal sequential action selection for multi-armed multi-action bandits with unknown parameters.
method Occupancy-Measured-Reward Index Policy (OMRIP) and R(MA)^2B-UCB algorithm.
result Asymptotically optimal policy with sub-linear regret and low computational complexity.
A classic setting of the stochastic K-armed bandit problem is considered in this note. In this problem it has been known that KL-UCB policy achieves the asymptotically optimal regret bound and KL-UCB+ policy empirically performs better than the KL-UCB policy although the regret bound for the original form of the KL-UCB…
The multi-armed bandit problem has been extensively studied under the stationary assumption. However in reality, this assumption often does not hold because the distributions of rewards themselves may change over time. In this paper, we propose a change-detection (CD) based framework for multi-armed bandit problems und…
UCB algorithm adapted for large-scale, non-sub-Gaussian problems.
problem Selecting the best alternative from a large set of options with non-sub-Gaussian performance distributions.
method Adapted UCB algorithm for non-sub-Gaussian settings, focusing on sample size and meta-UCB selection.
result UCB algorithms can achieve sample optimality in large-scale, non-sub-Gaussian problems.
Improved UCB method for stochastic bandits using distance tuning.
problem Improving performance in stochastic bandit problems.
method Tuning confidence bounds based on bandit distance.
result Empirically shows increased performance compared to existing methods.
We consider the sequential Bayesian optimization problem with bandit feedback, adopting a formulation that allows for the reward function to vary with time. We model the reward function using a Gaussian process whose evolution obeys a simple Markov model. We introduce two natural extensions of the classical Gaussian pr…
Designs adaptive controller for networked control systems with wireless data transmission.
problem Adaptive control in networked systems with unreliable wireless channels.
method Upper Confidence Bounds for Networked Control Systems (UCB-NCS) learning rule.
result Non-asymptotic performance guarantees with a regret bound of O(C√T).
Fine-grained gap-dependent regret bounds for reinforcement learning.
problem Achieving optimal regret bounds for reinforcement learning with suboptimality gaps.
method Developed novel analytical frameworks and refined algorithms for UCB-based and non-UCB-based reinforcement learning.
result Established the first fine-grained gap-dependent regret bounds for both UCB-based and non-UCB-based algorithms.
A new UCB algorithm for heavy-tailed bandits with near-optimal regret.
problem Sequential decision making in uncertain environments with heavy-tailed rewards.
method Data-driven, distribution-free UCB algorithm combining resampled median-of-means and UCB.
result Near-optimal regret bound for heavy-tailed distributions.
This paper improves GP-UCB by using a shifted exponential distribution for confidence parameters.
problem Theoretical confidence parameter in GP-UCB increases with iterations, leading to large values.
method Introduced IRGP-UCB, a randomized variant of GP-UCB using a shifted exponential distribution for confidence parameters.
result IRGP-UCB achieves sub-linear regret without increasing the confidence parameter.
GP-UCB performs suboptimally under certain conditions, as shown by a new regret lower bound.
problem The suboptimality of GP-UCB under polynomial effective optimism.
method Analysis of effective optimism level and new regret lower bound.
result GP-UCB is not minimax optimal under polynomial growth of effective optimism.
In this paper we propose and explore the k-Nearest Neighbour UCB algorithm for multi-armed bandits with covariates. We focus on a setting where the covariates are supported on a metric space of low intrinsic dimension, such as a manifold embedded within a high dimensional ambient feature space. The algorithm is concept…
A new method optimizes robustness measures under input uncertainty using randomized Gaussian process upper confidence bound.
problem Optimizing robustness measures under input uncertainty.
method Randomized robustness measure GP-UCB (RRGP-UCB) that samples β from a chi-squared-based distribution.
result RRGP-UCB provides tight bounds on expected regret.
UCB exploration improves best arm identification in fixed-budget settings.
problem Best arm identification in fixed-budget scenarios.
method Adaptive allocations based on upper confidence bounds (UCBs) with prior information learning.
result Empirically and theoretically efficient for Bayesian BAI problem with improved performance.
TS-UCB improves Thompson Sampling with minimal extra computation.
problem Online decision problems with bandit feedback.
method TS-UCB uses posterior samples and upper confidence bounds to select arms.
result TS-UCB achieves lower regret on various datasets.
UCB algorithm's arm-sampling behavior is revealed, leading to new insights and proofs.
problem Optimizing multi-armed bandit algorithms for worst-case scenarios.
method Analysis of UCB algorithm's arm-sampling behavior and process-level characterization.
result UCB's arm-sampling rates are asymptotically deterministic, regardless of problem complexity.
Paper proposes FMAB framework for federated learning with two models: approximate and exact.
problem Uncertainty in client sampling and suboptimality gap in federated multi-armed bandits.
method Developed a general FMAB framework and two specific models (approximate and exact), proposing Fed2-UCB for the approximate model.
result Achieved O(log(T)) regret in the approximate model and order-optimal regret in the exact model.
New method uses offline data to improve online bandit learning, even when distributions differ.
problem Improving online bandit learning with different offline and online distributions.
method MIN-UCB policy that adapts to offline data when informative, achieving tight regret bounds.
result MIN-UCB policy outperforms UCB policy with offline data and provides tight regret bounds.
A meta-UCB method combines stochastic bandit algorithms.
problem Combining multiple stochastic bandit algorithms efficiently.
method Meta-UCB procedure solving an N-armed bandit problem.
result Final regret depends only on the best base algorithm's regret.
FP-UCB algorithm achieves bounded regret for finitely parameterized multi-armed bandits.
problem Finitely parameterized multi-armed bandits with unknown but known parameter set.
method FP-UCB algorithm using structural information about the parameter set.
result FP-UCB achieves bounded regret under structural condition, logarithmic otherwise.
GP-UCB resolves sublinear regret for kernelized bandits.
problem Minimizing regret in kernelized bandit problems.
method Using a new regularization technique for kernel ridge estimators, improving GP-UCB's sublinear regret rate.
result GP-UCB achieves nearly optimal sublinear regret for the Matérn kernel.
Unified theory for UCB policies in total and max bandit problems.
problem Order optimality of UCB policies in max bandit problems.
method Unified definition of UCB policy using oracle quantity and failure count.
result UCB policies are order optimal in both total and max bandit problems.
New UCB algorithm for learning PSRs with tractable computation and accuracy.
problem Learning predictive state representations in sequential decision-making problems.
method Proposes a novel UCB-type algorithm with a bonus term to estimate PSRs accurately and efficiently.
result First known UCB-type approach for PSRs with guaranteed model accuracy and computational tractability.
This paper improves Bayesian optimization methods with tighter regret bounds and practical solutions.
problem Improving Bayesian optimization methods with tighter regret bounds and practical solutions.
method The paper analyzes and compares different acquisition functions (GP-UCB, TS, PIMS) to achieve tighter Bayesian cumulative regret bounds and address practical issues.
result PIMS achieves the tighter BCR bound and avoids hyperparameter tuning, unlike GP-UCB and TS.
New algorithm robust to outliers in Bayesian Optimization.
problem Vulnerability of Bayesian Optimization to extreme outliers.
method Introduces a new adversary with a frequency-bounded corruption budget and derives RCGP-UCB algorithm.
result Achieves sublinear regret in the presence of up to O ( T 1 / 4 ) O(T^{1/4}) O ( T 1/4 ) and O ( T 1 / 7 ) O(T^{1/7}) O ( T 1/7 ) corruptions with possibly infinite magnitude. New UCB-type algorithms reduce regret bounds for stochastic bandits with heavy and super heavy noise.
problem Improving regret bounds for stochastic bandits with heavy-tailed noise.
method General convex optimization methods with an inexact oracle, Clipped-SGD-UCB algorithm.
result Achieved an O ( log T K T log T ) O(\log T\sqrt{KT\log T}) O ( log T K T log T ) regret bound for symmetric noise, better than general lower bounds. Unified proof for various bandit algorithms with logarithmic regret.
problem Achieving logarithmic regret in stochastic bandit algorithms.
method Minimal high-probability concentration condition and two deterministic lemmas.
result Unified proofs for classical and contemporary bandit algorithms.
Greedy algorithms outperform UCB in many-armed bandit problems.
problem Optimizing multi-armed bandit problems with many arms.
method Subsampled UCB and greedy algorithms comparison.
result Greedy algorithms achieve optimal regret in many-armed bandit problems.
New algorithm prevents strategic replication in multi-armed bandit problems.
problem Strategic replication by agents can exploit bandit algorithms' balance.
method Designs Hierarchical UCB (H-UCB) and Robust Hierarchical UCB (RH-UCB) algorithms.
result Achieves O ( ln T ) O(\ln T) O ( ln T ) -regret and sublinear regret in realistic scenarios. A new algorithm for competing agents in a two-sided market setting.
problem Decentralized competition between agents in a two-sided market with unknown valuations.
method UCB-D3 algorithm for UCB with Decentralized Dominant-arm Deletion.
result UCB-D3 is order optimal and achieves a new regret lower bound.
This paper is about index policies for minimizing (frequentist) regret in a stochastic multi-armed bandit model, inspired by a Bayesian view on the problem. Our main contribution is to prove that the Bayes-UCB algorithm, which relies on quantiles of posterior distributions, is asymptotically optimal when the reward dis…
RAVEN-UCB addresses non-stationary MAB problems with tighter regret bounds.
problem Non-stationary environments in multi-armed bandits.
method Combines variance-aware adaptation with three innovations: confidence bounds, adaptive control, and recursive updates.
result Achieves tighter regret bounds than UCB1 and UCB-V.
UCB algorithms improve on bandit problems with precise regret analysis and adaptive inference.
problem Understanding the performance and statistical inference of UCB algorithms in multi-armed bandit problems.
method Deterministic characterization of arm pulls and precise regret analysis.
result UCB algorithms' maximal regret deviates from minimax regret by a logarithmic factor, and the Lai-Robbins formula is exact only under specific conditions.
New algorithm outperforms existing ones in multi-player bandit problems without sensing.
problem Decentralized multi-player multi-armed bandit problem without collision or sensing info.
method Randomized Selfish KL-UCB, inspired by Selfish KL-UCB, with low complexity.
result Randomized Selfish KL-UCB outperforms state-of-the-art algorithms in almost all environments.
Characterizes UCB algorithm performance in bandit problems.
problem Optimizing UCB algorithm performance in stochastic bandit environments.
method Novel perturbation analysis to characterize CLT of pulls and means.
result Smooth interpolation of pseudo-regret between large and small gap regimes.
UCB algorithm provides stable sample means for sequential data.
problem Challenges in inferential tasks with sequential data.
method Stability property of UCB algorithm for multiarmed bandit problems.
result UCB algorithm ensures asymptotically normal sample means.
ET-GP-UCB optimizes time-varying functions without knowing change rates.
problem Sequentially optimizing a time-varying objective function with unknown change rates.
method Event-triggered Bayesian optimization with adaptive resets based on probabilistic uniform error bounds.
result ET-GP-UCB outperforms other GP-UCB algorithms in synthetic and real-world data.
In this work, we address the open problem of finding low-complexity near-optimal multi-armed bandit algorithms for sequential decision making problems. Existing bandit algorithms are either sub-optimal and computationally simple (e.g., UCB1) or optimal and computationally complex (e.g., kl-UCB). We propose a boosting a…