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 Added Most Hyped Most Active Needs Verification Most Verified

Showing 201–225 of 1262 papers

Title	Date	Tasks	Status	Score
Flooding with Absorption: An Efficient Protocol for Heterogeneous Bandits over Complex Networks	Mar 9, 2023	Decision MakingMulti-Armed Bandits	CodeCode Available	5
Combining Diverse Information for Coordinated Action: Stochastic Bandit Algorithms for Heterogeneous Agents	Aug 6, 2024	Multi-Armed BanditsSensitivity	CodeCode Available	5
Combinatorial Bandits under Strategic Manipulations	Feb 25, 2021	Multi-Armed BanditsRecommendation Systems	CodeCode Available	5
On-line Adaptative Curriculum Learning for GANs	Jul 31, 2018	Multi-Armed BanditsStochastic Optimization	CodeCode Available	5
Online Limited Memory Neural-Linear Bandits with Likelihood Matching	Feb 7, 2021	Efficient ExplorationMulti-Armed Bandits	CodeCode Available	5
Online Matching: A Real-time Bandit System for Large-scale Recommendations	Jul 29, 2023	Multi-Armed BanditsRecommendation Systems	CodeCode Available	5
Model selection for contextual bandits	Jun 3, 2019	modelModel Selection	CodeCode Available	5
Budgeted Multi-Armed Bandits with Asymmetric Confidence Intervals	Jun 12, 2023	Multi-Armed Bandits	CodeCode Available	5
Information-Directed Selection for Top-Two Algorithms	May 24, 2022	Multi-Armed BanditsThompson Sampling	CodeCode Available	5
Optimal Learning for Structured Bandits	Jul 14, 2020	Decision MakingDecision Making Under Uncertainty	CodeCode Available	5
From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization	Mar 7, 2019	compressed sensingMulti-Armed Bandits	CodeCode Available	5
Optimistic Whittle Index Policy: Online Learning for Restless Bandits	May 30, 2022	Multi-Armed Bandits	CodeCode Available	5
Offline Contextual Bandits with Overparameterized Models	Jun 27, 2020	Multi-Armed BanditsQ-Learning	CodeCode Available	5
Combinatorial Multi-armed Bandits for Resource Allocation	May 10, 2021	Multi-Armed Bandits	CodeCode Available	5
Conditionally Risk-Averse Contextual Bandits	Oct 24, 2022	ManagementMulti-Armed Bandits	CodeCode Available	5
Persistency of Excitation for Robustness of Neural Networks	Nov 4, 2019	Multi-Armed Bandits	CodeCode Available	5
Piecewise-Stationary Multi-Objective Multi-Armed Bandit with Application to Joint Communications and Sensing	Feb 10, 2023	Change DetectionMulti-Armed Bandits	CodeCode Available	5
Causal Contextual Bandits with Adaptive Context	May 28, 2024	Multi-Armed Bandits	CodeCode Available	5
Addressing the Long-term Impact of ML Decisions via Policy Regret	Jun 2, 2021	Multi-Armed Bandits	CodeCode Available	5
Practical Bayesian Learning of Neural Networks via Adaptive Optimisation Methods	Nov 8, 2018	Multi-Armed BanditsThompson Sampling	CodeCode Available	5
Causally Abstracted Multi-armed Bandits	Apr 26, 2024	Decision MakingMulti-Armed Bandits	CodeCode Available	5
Censored Semi-Bandits: A Framework for Resource Allocation with Censored Feedback	Sep 4, 2019	Multi-Armed Bandits	CodeCode Available	5
Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles	Mar 3, 2017	Multi-Armed Bandits	CodeCode Available	5
Quantum Natural Policy Gradients: Towards Sample-Efficient Reinforcement Learning	Apr 26, 2023	Multi-Armed Banditsreinforcement-learning	CodeCode Available	5
Doubly-Robust Lasso Bandit	Jul 26, 2019	Multi-Armed BanditsRecommendation Systems	CodeCode Available	5

Show:10 25 50

← PrevPage 9 of 51Next →

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	NeuralLinear FullPosterior-MR	Cumulative regret	1.92	—	Unverified
2	Linear FullPosterior-MR	Cumulative regret	1.82	—	Unverified