Preprintgreen2011

Efficient Optimal Learning for Contextual Bandits

Miroslav Dudı́k · Daniel Hsu · Satyen Kale · Nikos Karampatziakis · John C. Langford · Lev Reyzin +1 more

174 citations0/0 files storedarXiv (Cornell University)

No readable copy stored yet — this record is metadata only.

Advanced Bandit Algorithms Research Reinforcement Learning in Robotics Machine Learning and Algorithms

Abstract

We address the problem of learning in an online setting where the learner repeatedly observes features, selects among a set of actions, and receives reward for the action taken. We provide the first efficient algorithm with an optimal regret. Our algorithm uses a cost sensitive classification learner as an oracle and has a running time $\mathrm{polylog}(N)$, where $N$ is the number of classification rules among which the oracle might choose. This is exponentially faster than all previous algorithms that achieve optimal regret in this setting. Our formulation also enables us to create an algorithm with regret that is additive rather than multiplicative in feedback delay as in all previous work.

Citations in this library

Stored only when both papers are in the corpus — 174 citations exist upstream.

References

1997A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting 2002Finite-time Analysis of the Multiarmed Bandit Problem 2002The Nonstochastic Multiarmed Bandit Problem 2012Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting 2003Using confidence bounds for exploitation-exploration trade-offs 2004Efficient algorithms for online decision problems 2006Action Elimination and Stopping Conditions for the Multi-Armed Bandit and Reinforcement Learning Problems 2007The Epoch-Greedy algorithm for contextual multi-armed bandits

Cited by

2017From Ads to Interventions: Contextual Bandits in Mobile Health 2013Finite-Time Analysis of Kernelised Contextual Bandits 2021Adaptive Treatment Assignment in Experiments for Policy Choice 2015Online learning under delayed feedback 2015Bandits with unobserved confounders: a causal approach 2016Dynamic Pricing with Demand Covariates

Imported from OpenAlex (CC0) — nothing here is generated.