Results 61 to 70 of about 313 (110)
, 2014 In the 1970’s John Gittins discovered that multi-armed bandits, an important class of models for the dynamic allocation of a single key resource among a set of competing projects, have optimal solutions of index form. At each decision epoch such policies
Minty, John +7 more
core +1 more source
The Gittins Index: A Design Principle for Decision Making Under Uncertainty
The Gittins index is a tool that optimally solves a variety of decision-making problems involving uncertainty, including multi-armed bandit problems, minimizing mean latency in queues, and search problems like the Pandora's box model. However, despite the above examples and later extensions thereof, the space of problems that the Gittins index can ...
Ziv Scully, Alexander Terenin
openaire +2 more sources
Gittins, Mrs H, [No Service Number]
, 2017 This record was harvested from a previous catalogue system and will be withdrawn in 2025. Information in this record may be superseded or incomplete.
Australian Red Cross Society, National Office
core
—Discussion on “Website Morphing” by Hauser, Urban, Liberali, and Braun
These comments are a tribute to an impressive paper and suggestions for clarification of some fairly minor issues.website morphing, Gittins ...
John Gittins
core +1 more source
Some results on the Gittins index for a normal reward process
, 2006 We consider the Gittins index for a normal distribution with unknown mean $θ$ and known variance where $θ$ has a normal prior. In addition to presenting some monotonicity properties of the Gittins index, we derive an approximation to the Gittins index by embedding the (discrete-time) normal setting into the continuous-time Wiener process setting in ...
openaire +3 more sources
Regret Analysis of the Finite-Horizon Gittins Index Strategy for Multi-Armed Bandits
CoRR, 2015 I analyse the frequentist regret of the famous Gittins index strategy for multi-armed bandits with Gaussian noise and a finite horizon. Remarkably it turns out that this approach leads to finite-time regret guarantees comparable to those available for the popular UCB algorithm.
openaire +3 more sources
Two-stage index computation for bandits with switching penalties I : switching costs [PDF]
, 2007 This paper addresses the multi-armed bandit problem with switching costs. Asawa and Teneketzis (1996) introduced an index that partly characterizes optimal policies, attaching to each bandit state a "continuation index" (its Gittins index) and a ...
Niño-Mora, José, Niño Mora, José
core
User adaptive Web morphing : an implementation of a Web-based Bayesian inference engine with Gittins' Index [PDF]
, 2008 Thesis (M. Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.Some sections in thesis unnumbered.Includes bibliographical references.Imagine a world where computers are able to present desired ...
Lee, Clarence, M. Eng. Massachusetts Institute of Technology
core
Keeping Your Options Open [PDF]
In standard models of experimentation, the costs of project development consist of (i) the direct cost of running trials as well as (ii) the implicit opportunity cost of leaving alternative projects idle. Another natural type of experimentation cost, the
Jean Guillaume Forand
core
On Gittins' index theorem in continuous time
We give a new and comparably short proof of Gittins' index theorem for dynamic allocation problems of the multi-armed bandit type in continuous time under minimal assumptions.
Küchler, Christian, Bank, Peter
core