arXiv research

The paper proves the convergence of Q-value for Gaussian rewards.

Method predicts future rewards from past actions in a linear Gaussian system.

New algorithm reduces regret in multi-armed bandit problems with Gaussian rewards.

Thompson Sampling bounds for contextual bandits with sub-Gaussian rewards.

A new method resolves non-identifiability in reward modeling using anchor labels.

Paper improves SLCB regret bound for bounded noise.

A new method optimizes in nonstationary environments with many arms efficiently.

New algorithm for recommending best arms with aggregated feedback.

New algorithm uses machine learning to predict rewards for decision-making problems.

New acquisition function for extreme rewards in bandits.

Nonparametric Thompson Sampling achieves optimal regret for risk-averse bandits with sub-Gaussian rewards.

We here adopt Bayesian nonparametric mixture models to extend multi-armed bandits in general, and Thompson sampling in particular, to scenarios where there is reward model uncertainty. In the stochastic multi-armed bandit, the reward for the played arm is generated from an unknown distribution. Reward uncertainty, i.e.…

Iterative tilting fine-tunes diffusion models for reward-tilted distributions.

A bandit algorithm reduces regret in noisy, communication-constrained feedback.

Inspired by the Reward-Biased Maximum Likelihood Estimate method of adaptive control, we propose RBMLE -- a novel family of learning algorithms for stochastic multi-armed bandits (SMABs). For a broad range of SMABs including both the parametric Exponential Family as well as the non-parametric sub-Gaussian/Exponential f…

A new algorithm balances global reward and group constraints in federated multi-armed bandits.

A new algorithm uses concavity in Gaussian processes to optimize decisions in bandit problems.

The paper tackles resource allocation for arms with unknown and random rewards, achieving optimal regret bounds.

New algorithms for generalized linear bandits with unknown reward functions.

The study analyzes how neural reward models learn features for policy optimization in a Gaussian single-index model.

The paper analyzes the reward improvement of aligned policies in large language models.

Polynomial-time method solves complex combinatorial semi-bandits.

New algorithm reduces worst-case regret for heavy-tailed bandits.

This paper extends the MAB problem to consider risk-reward tradeoffs.

We investigate the use of bootstrapping in the bandit setting. We first show that the commonly used non-parametric bootstrapping (NPB) procedure can be provably inefficient and establish a near-linear lower bound on the regret incurred by it under the bandit model with Bernoulli rewards. We show that NPB with an approp…

A novel approach uses an ensemble of Gaussian processes for robust and adaptive reinforcement learning.

Thompson Sampling shows polynomial regret for combinatorial semi-bandits with subgaussian rewards.

Optimizing rewards under budget constraints with correlated costs and rewards.

New algorithms handle heavy-tailed rewards in reinforcement learning.

KL-MS improves regret bounds for multi-armed bandits with bounded rewards.

A new algorithm for bandits with hierarchical rewards.

We investigate and provide new insights on the sampling rule called Top-Two Thompson Sampling (TTTS). In particular, we justify its use for fixed-confidence best-arm identification. We further propose a variant of TTTS called Top-Two Transportation Cost (T3C), which disposes of the computational burden of TTTS. As our …

The stochastic multi-armed bandit problem is well understood when the reward distributions are sub-Gaussian. In this paper we examine the bandit problem under the weaker assumption that the distributions have moments of order 1+ε, for some $ε\in (0,1]$. Surprisingly, moments of order 2 (i.e., finite variance) are suffi…

Improved GP bandit algorithms for noiseless, varying noise, and RKHS norms.

Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors), and is therefore not credible. In addition, for applications such as robotics, …

New algorithm for shareable arms with load-dependent rewards in stochastic bandits.

A novel algorithm minimizes regret in a multi-agent bandit problem with time-varying random graphs and heterogeneous rewards.

The paper proposes a model reward scheme for collaborative ML based on Shapley value and information gain.

This paper presents a novel nonmyopic adaptive Gaussian process planning (GPP) framework endowed with a general class of Lipschitz continuous reward functions that can unify some active learning/sensing and Bayesian optimization criteria and offer practitioners some flexibility to specify their desired choices for defi…

New strategy optimally identifies best arm in unknown variance Gaussian bandits.

Optimizes reward learning design for complex tasks using nonparametric methods.

Study on identifying most preferred policy in bandits with vector-valued rewards.

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…

The paper identifies all ε-optimal arms in a bandit problem with Gaussian rewards.

New algorithm reduces semi-bandit regret using covariance estimates.

DS-TS adapts to abrupt and smooth changes in bandit problems.

Improved Bayesian regret bound for linear Thompson sampling with general distributions.

Paper tackles constrained bandit problems with a new learning framework.