SOTAVerified

Multi-Armed Bandits

Multi-armed bandits refer to a task where a fixed amount of resources must be allocated between competing resources that maximizes expected gain. Typically these problems involve an exploration/exploitation trade-off.

( Image credit: Microsoft Research )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 876–900 of 1262 papers

TitleStatusHype
Non-Stationary Off-Policy Optimization—0
Explicit Best Arm Identification in Linear Bandits Using No-Regret Learners—0
Quantile Multi-Armed Bandits: Optimal Best-Arm Identification and a Differentially Private Scheme—0
TS-UCB: Improving on Thompson Sampling With Little to No Additional Computation—0
Bandits with Partially Observable Confounded Data—0
Gaussian Gated Linear NetworksCode0
Distributionally Robust Batch Contextual Bandits—0
Simultaneously Learning Stochastic and Adversarial Episodic MDPs with Known Transition—0
Meta-Learning Bandit Policies by Gradient Ascent—0
Online Learning in Iterated Prisoner's Dilemma to Mimic Human BehaviorCode0
Contextual Bandits with Side-Observations—0
Concurrent Decentralized Channel Allocation and Access Point Selection using Multi-Armed Bandits in multi BSS WLANs—0
Locally Differentially Private (Contextual) Bandits LearningCode0
(Locally) Differentially Private Combinatorial Semi-Bandits—0
To update or not to update? Delayed Nonparametric Bandits with Randomized Allocation—0
Greedy Algorithm almost Dominates in Smoothed Contextual Bandits—0
Neural Network Retraining for Model Serving—0
Learning to Rank in the Position Based Model with Bandit Feedback—0
Thompson Sampling for Linearly Constrained BanditsCode0
Sequential Batch Learning in Finite-Action Linear Contextual Bandits—0
Power Constrained BanditsCode0
Exploration with Limited Memory: Streaming Algorithms for Coin Tossing, Noisy Comparisons, and Multi-Armed Bandits—0
Hawkes Process Multi-armed Bandits for Disaster Search and Rescue—0
Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability—0
Optimal No-regret Learning in Repeated First-price Auctions—0
Show:102550
← PrevPage 36 of 51Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1NeuralLinear FullPosterior-MRCumulative regret1.92—Unverified
2Linear FullPosterior-MRCumulative regret1.82—Unverified