arXiv research

Fine-grained gap-dependent regret bounds for reinforcement learning.

Paper proposes CVaR-TS for risk-constrained MAB problems.

New algorithm reduces sample complexity for Top Two method.

CMOSS algorithm reduces regret in combinatorial semi-bandits with efficient computation.

A TS algorithm improves performance in multi-task bandits with transfer.

FGTSVA improves Thompson Sampling for contextual bandits with optimal variance-aware regret.

New algorithm for maximizing revenue in multinomial logistic bandits.

We study the stochastic contextual bandit problem, where the reward is generated from an unknown function with additive noise. No assumption is made about the reward function other than boundedness. We propose a new algorithm, NeuralUCB, which leverages the representation power of deep neural networks and uses a neural…

The design and performance analysis of bandit algorithms in the presence of stage-wise safety or reliability constraints has recently garnered significant interest. In this work, we consider the linear stochastic bandit problem under additional \textit{linear safety constraints} that need to be satisfied at each round.…

New algorithm eliminates arms to minimize regret in complex bandit problems.

New algorithm tackles stochastic bandits with varying arm-dependent delays.

New algorithm minimizes regret in multi-agent bandit problem with probabilistic communication.

We present a new recommendation setting for picking out two items from a given set to be highlighted to a user, based on contextual input. These two items are presented to a user who chooses one of them, possibly stochastically, with a bias that favours the item with the higher value. We propose a second-order algorith…

Maximin UCB algorithm optimizes energy harvesting for sensor networks.

New algorithm explores reinforcement learning with noisy data.

Quantum UCB algorithm reduces reinforcement learning regret exponentially.

We consider a novel stochastic multi-armed bandit setting, where playing an arm makes it unavailable for a fixed number of time slots thereafter. This models situations where reusing an arm too often is undesirable (e.g. making the same product recommendation repeatedly) or infeasible (e.g. compute job scheduling on ma…

New algorithm optimizes noisy, potentially corrupted functions.

A UCB algorithm reduces regret in cooperative multi-agent graph bandits.

Proposes a new sampling method for online learning with cumulative oversampling.

Statistical model checking for PCTL on MDPs using reinforcement learning.

This work deals with parallel optimization of expensive objective functions which are modeled as sample realizations of Gaussian processes. The study is formalized as a Bayesian optimization problem, or continuous multi-armed bandit problem, where a batch of q > 0 arms is pulled in parallel at each iteration. Several a…

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 superior to Upper Confidence Bound (UCB) algorithms for cascading bandits, theoretica…

New bandit model accounts for user departures in recommender systems.

Bandit algorithms have various application in safety-critical systems, where it is important to respect the system constraints that rely on the bandit's unknown parameters at every round. In this paper, we formulate a linear stochastic multi-armed bandit problem with safety constraints that depend (linearly) on an unkn…

New UCB algorithm for learning PSRs with tractable computation and accuracy.

UCB exploration improves best arm identification in fixed-budget settings.

Adaptive KL-UCB algorithm for Markov and i.i.d. rewards.

Wireless systems perform rate adaptation to transmit at highest possible instantaneous rates. Rate adaptation has been increasingly granular over generations of wireless systems. The base-station uses SINR and packet decode feedback called acknowledgement/no acknowledgement (ACK/NACK) to perform rate adaptation. SINR i…

Contrastive UCB improves RL by learning feature representations efficiently.

DMNL bandits optimize assortment choices balancing relevance and diversity.

We study the online influence maximization problem in social networks under the independent cascade model. Specifically, we aim to learn the set of "best influencers" in a social network online while repeatedly interacting with it. We address the challenges of (i) combinatorial action space, since the number of feasibl…

Master-slave architecture tackles combinatorial multi-armed bandits with diversity constraints.

Improved UCB method for stochastic bandits using distance tuning.

Algorithm optimizes bandit decisions with changing action sets using Gaussian processes.

This paper analyzes MORL and proposes efficient algorithms to learn Pareto optimal policies.

EgalMAB solves fair resource allocation in stochastic bandits.

This paper introduces a novel framework to construct the region of attraction (ROA) of a power system centered around a stable equilibrium by using stable state trajectories of system dynamics. Most existing works on estimating ROA rely on analytical Lyapunov functions, which are subject to two limitations: the analyti…

Unified theory for UCB policies in total and max bandit problems.

The paper tackles causal bandits for SEMs, proposing algorithms that avoid estimating $2^N$ reward distributions.

In this paper, we study the dynamic assortment optimization problem under a finite selling season of length $T$. At each time period, the seller offers an arriving customer an assortment of substitutable products under a cardinality constraint, and the customer makes the purchase among offered products according to a d…

A decentralized policy achieves logarithmic regret for multi-agent MAB problems with communication constraints.

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

A novel bandit problem with context-dependent rewards and blocking.

Proposes EE-Net for neural exploration in contextual bandits.

New methods for estimating and inferring nonparametric structural functions and elasticities.

Unified framework for scalable black-box optimization.

A new method optimizes material discovery by balancing exploration and exploitation.