Asymptotically Efficient Adaptive Allocation Rules

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical Learning Theory

Citations in the corpus

Machine Learning Methods That Economists Should Know About (2019, background): “Thompson sampling (Scott [2010], Thompson [1933]) and Upper Confidence Bounds (UCB, Lai and Robbins [1985]) can be viewed as a simple example of reinforcement learning (Sutton et al.”
Hyper-Parameter Optimization: A Review of Algorithms and Applications (2020, background): “Various acquisition functions have been proposed in previous studies, including the probability of improvement (Kushner, 1964), GP upper confidence bound (GP-UCB) (Lai and Robbins, 1985; Srinivas et al., 2009), predictive entropy search (Hernández-Lobato et al., 2014), and even a portfolio containi”
Balanced Linear Contextual Bandits (2018, methodology): “2018) and Upper Confidence Bounds (UCB) (Lai and Robbins 1985), (Auer, CesaBianchi, and Fischer 2002) are two different methods which are highly effective in dealing with the exploration vs.”
Estimation Considerations in Contextual Bandits (2017, methodology): “Thompson sampling [61, 55, 5, 52] and upper confidence bound (UCB) [40, 12] are two different methods for assigning contexts to arms which are highly effective in dealing with the exploration-exploitation trade-off.”
Learning to Learn for Global Optimization of Black Box Functions (2016, background): “…2015], probability of improvement [Kushner, 1964, Jones et al., 1998], expected improvement [Moˇckus et al., 1978, Jones et al., 1998, Jones, 2001, Brochu et al., 2009, Snoek et al., 2012, Wang and de Freitas, 2014], upper conﬁdence bounds [Lai and Robbins, 1985, Srinivas et al., 2010], and so on.”
The Uncertainty Bellman Equation and Exploration (2017, background): “For this reason, most provably-efficient approaches to reinforcement learning rely upon the optimism in the face of uncertainty (OFU) heuristic [14, 13, 7].”
Fairness in Learning: Classic and Contextual Bandits (2016, methodology): “First, we study the classic stochastic multi-armed bandit problem [Lai and Robbins, 1985, Katehakis and Robbins, 1995].”
Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems (2012, neutral): “2.1 Optimism in face of uncertainty 9 2.2 Upper Confidence Bound (UCB) strategies 10 2.3 Lower bound 12 2.4 Refinements and bibliographic remarks 16”
PAC Bounds for Discounted MDPs (2012, background): “The approach has been successful in obtaining uniform sample complexity (or regret) bounds in various domains where the exploration/exploitation problem is an issue (Lai and Robbins, 1985; Agrawal, 1995; Auer et al., 2002; Strehl and Littman, 2005; Auer and Ortner, 2007; Auer et al., 2010; Auer, 201”
Learning to Optimize via Posterior Sampling (2013, background): “Indeed, algorithms based on this principle have been shown to be asymptotically efficient in terms of both regret (Lai and Robbins [26]) and Bayesian regret (Lai [25]), to satisfy order optimal minimax regret bounds (Audibert and Bubeck [8]), to satisfy order optimal bounds on regret and Bayesian re”
(More) Efficient Reinforcement Learning via Posterior Sampling (2013, background): “To offset this, the majority of provably efficient learning algorithms use a principle known as optimism in the face of uncertainty [3] to encourage exploration.”
A Brief Survey of Deep Reinforcement Learning (2017, neutral): “One of the main principled exploration strategies is the upper confidence bound (UCB) algorithm, based on the principle of “optimism in the face of uncertainty” [56].”
Efficient Policy Learning (2017, neutral): “2Our setup, where we want to learn a policy based on already collected observational data, is in contrast to the online “contextual bandit” setup where the practitioner seeks to learn a decision rule while actively making treatment allocation decisions for incoming subjects (e.g., Agarwal et al., 20”
Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis (2012, background): “Their result, which holds for more general classes of reward distributions, leads to the definition of asymptotically optimal policies as policies that satisfy (2) with equality.”
Online Learning: A Comprehensive Survey (2018, background): “…variant of Bayesian Bandit is called the Bayes-UCB algorithm (Kaufmann et al., 2012), which is a UCB-like algorithm, where the upper confidence bounds are based on the quantiles of Beta posterior distributions, and is able to achieve the lower bound of Lai and Robbins (1985) for Bernoulli rewards.”
Further Optimal Regret Bounds for Thompson Sampling (2012, methodology): “Then the expected total regret in time T is given by P Other performance measures include PAC-style guarantees; we do not consider those measures here.”