conftrace_

multi-armed bandit

1098 papers

Explore in graph

Also known as

MAB

Co-occurring keywords

regret bound (1926) online learning (1777) stochastic optimization (1060) thompson sampling (237) upper confidence bound (197) regret minimization (315) online algorithm (445) sample complexity (1169) contextual bandit (381) best arm identification (85)

Papers

Tuning Mixed Input Hyperparameters on the Fly for Efficient Population Based AutoRL NIPS 2021
Bandits with many optimal arms NIPS 2021
Bandits with Knapsacks beyond the Worst Case NIPS 2021
Mean Field Equilibrium in Multi-Armed Bandit Game with Continuous Reward IJCAI 2021
Heterogeneous Multi-player Multi-armed Bandits: Closing the Gap and Generalization NIPS 2021
Fair Algorithms for Multi-Agent Multi-Armed Bandits NIPS 2021
Non-stationary Reinforcement Learning without Prior Knowledge: an Optimal Black-box Approach COLT 2021
Recurrent Submodular Welfare and Matroid Blocking Semi-Bandits NIPS 2021
Combinatorial Pure Exploration with Bottleneck Reward Function NIPS 2021
Fair Exploration via Axiomatic Bargaining NIPS 2021
Adaptive Discretization for Adversarial Lipschitz Bandits COLT 2021
On Optimal Robustness to Adversarial Corruption in Online Decision Problems NIPS 2021
Stochastic bandits with groups of similar arms. NIPS 2021
Indexed Minimum Empirical Divergence for Unimodal Bandits NIPS 2021
Online Sign Identification: Minimization of the Number of Errors in Thresholding Bandits NIPS 2021
A/B/n Testing with Control in the Presence of Subpopulations NIPS 2021
Multi-Armed Bandits with Bounded Arm-Memory: Near-Optimal Guarantees for Best-Arm Identification and Regret Minimization NIPS 2021
Pure Exploration in Kernel and Neural Bandits NIPS 2021
Causal Bandits with Unknown Graph Structure NIPS 2021
DEHB: Evolutionary Hyberband for Scalable, Robust and Efficient Hyperparameter Optimization IJCAI 2021
Parametric Graph for Unimodal Ranking Bandit ICML 2021
Asymptotically Best Causal Effect Identification with Multi-Armed Bandits NIPS 2021
Problem Dependent View on Structured Thresholding Bandit Problems ICML 2021
Combinatorial Blocking Bandits with Stochastic Delays ICML 2021
Addressing the Long-term Impact of ML Decisions via Policy Regret IJCAI 2021