Categories Companies Research

Loading the SOTA2 catalog…

Explore

Categories Companies Research

Contribute

Join SOTA2 Contact

SOTA2

© 2026 SOTA2

Build in Bellevue, USA

WizWand is now SOTA2 Research

Papers Benchmarks Datasets Tasks

Regret Minimization research benchmarks – Page 3 · SOTA2 Research

Regret Minimization

Benchmarks

Dataset NameSOTA MethodSort

Dataset NameSOTA methodMetricTrendResultsLast Updated

F_SYM Symmetric p-th order Homogeneous Polynomials (stochastic settings)

1Regret

1

Feb 27, 2026

Linear Bandit Theoretical Setting

Auer, Chu et al.

3Regret Bound

1

Jun 30, 2026

Ranking Bandits

—

—Primary metric

0

Jun 30, 2026

PS-CB (Piecewise Stationary Contextual Bandits)

—

—Primary metric

0

Jun 16, 2026

PS-KB (Piecewise Stationary Kernel Bandits)

—

—Primary metric

0

Jun 16, 2026

—

—Primary metric

0

Jun 16, 2026

—

—Primary metric

0

Jun 16, 2026

—

—Primary metric

0

Jun 16, 2026

—

—Primary metric

0

Jun 16, 2026

MO-MAB Theoretical

—

—Primary metric

0

Jun 9, 2026

Adversarial values

—

—Primary metric

0

May 20, 2026

Full-feedback mechanisms with Adversarial Values

—

—Primary metric

0

May 20, 2026

Bilateral Trade Adversarial Valuations

—

—Primary metric

0

May 20, 2026

Linear Bandits Under-explored offline regime

—

—Primary metric

0

May 13, 2026

Linear Bandits Moderately-explored offline regime

—

—Primary metric

0

May 13, 2026

Linear Bandits Well-explored offline regime

—

—Primary metric

0

May 13, 2026

Contextual Dueling Bandits (CDB)

—

—Primary metric

0

May 12, 2026

Contextual Multi-Armed Bandits (CMAB)

—

—Primary metric

0

May 12, 2026

Multi-Armed Bandits (MABs) Stochastic i.i.d. setting

—

—Primary metric

0

May 12, 2026

K-armed contextual bandit Logistic reward (theoretical bound)

—

—Primary metric

0

Apr 27, 2026

KL-regularized Bandits Eluder Dimension

—

—Primary metric

0

Mar 4, 2026

KL-regularized Bandits Preference w/ Eluder Dimension

—

—Primary metric

0

Mar 4, 2026

Reinforcement Learning with linear function approximation Gap-dependent Theoretical Bound

—

—Primary metric

0

Feb 26, 2026

Multinomial Logistic Bandit

—

—Primary metric

0

Feb 26, 2026

Binary Logistic Bandit

—

—Primary metric

0

Feb 26, 2026

Page 3 of 5

Popular datasets

KL-regularized Bandits Bilateral Trade K-armed bandits Synthetic MDP with Tucker rank

Follow for updates

Join SOTA2 Contact