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 411–420 of 1262 papers

TitleStatusHype
Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism—0
Efficient Algorithms for Finite Horizon and Streaming Restless Multi-Armed Bandit Problems—0
Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts—0
Efficient and Optimal Policy Gradient Algorithm for Corrupted Multi-armed Bandits—0
Efficient and Robust Algorithms for Adversarial Linear Contextual Bandits—0
Efficient Automatic CASH via Rising Bandits—0
Efficient Benchmarking of NLP APIs using Multi-armed Bandits—0
Efficient Contextual Bandits in Non-stationary Worlds—0
Cost-Efficient Distributed Learning via Combinatorial Multi-Armed Bandits—0
Constrained Policy Optimization for Controlled Self-Learning in Conversational AI Systems—0
Show:102550
← PrevPage 42 of 127Next →

Benchmark Results

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