Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems (Q6167036): Difference between revisions

Latest revision as of 19:04, 30 December 2024

scientific article; zbMATH DE number 7708608

Language	Label	Description	Also known as
English	Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems	scientific article; zbMATH DE number 7708608

Statements

instance of

scholarly article

0 references

title

Empirical Gittins index strategies with \(\varepsilon\)-explorations for multi-armed bandit problems (English)

0 references

published in

Computational Statistics and Data Analysis

0 references

publication date

7 July 2023

0 references

zbMATH Keywords

multi-armed bandit problem

0 references

reinforcement learning

0 references

rewarded Markov process

0 references

Gittins index

0 references

empirical Gittins index

0 references

MaRDI profile type

MaRDI publication profile

0 references

full work available at URL

https://doi.org/10.1016/j.csda.2022.107610

0 references

cites work

Sample mean based index policies by <i>O</i>(log <i>n</i>) regret for the multi-armed bandit problem

0 references

Finite-time analysis of the multiarmed bandit problem

0 references

Q4998881

0 references

Methods and Applications of Statistics in Clinical Trials

0 references

On Gittins' index theorem in continuous time

0 references

A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches

0 references

Optimal stochastic scheduling

0 references

On the Whittle index of Markov modulated restless bandits

0 references

General Gittins index processes in discrete time.

0 references

Dynamic allocation problems in continuous time

0 references

Synchronization and optimality for multi-armed bandit problems in continuous time

0 references

Continuous-time allocation indices and their discrete-time approximation

0 references

Consistency of Sequential Bayesian Sampling Policies

0 references

Q4197923

0 references

Q4057976

0 references

On Bayesian models in stochastic scheduling

0 references

Q4692329

0 references

Multi‐Armed Bandit Allocation Indices

0 references

Multi-armed bandit problem revisited

0 references

Gittins indices in the dynamic allocation problem for diffusion processes

0 references

Lévy bandits: Multi-armed bandits driven by Lévy processes

0 references

Multi-armed bandits in discrete and continuous time

0 references

On Bayesian index policies for sequential resource allocation

0 references

A Survey of Some Results in Stochastic Adaptive Control

0 references

Asymptotically efficient adaptive allocation rules

0 references

Open bandit processes and optimal scheduling of queueing networks

0 references

Adaptive treatment allocation and the multi-armed bandit problem

0 references

The Multi-Armed Bandit With Stochastic Plays

0 references

ON THE OPTIMALITY OF AN INDEX RULE IN MULTICHANNEL ALLOCATION FOR SINGLE-HOP MOBILE NETWORKS WITH MULTIPLE SERVICE CLASSES

0 references

Bandit Algorithms

0 references

On the Whittle Index for Restless Multiarmed Hidden Markov Bandits

0 references

A minimax and asymptotically optimal algorithm for stochastic bandits

0 references

Dynamic priority allocation via restless bandit marginal productivity indices

0 references

Some aspects of the sequential design of experiments

0 references

Linearly Parameterized Bandits

0 references

Q4626283

0 references

A short proof of the Gittins index theorem

0 references

Extensions of the multiarmed bandit problem: The discounted case

0 references

INDEXABILITY AND OPTIMAL INDEX POLICIES FOR A CLASS OF REINITIALISING RESTLESS BANDITS

0 references

Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges

0 references

On the Gittins index for multiarmed bandits

0 references

Branching Bandit Processes

0 references

Q3882215

0 references

Arm-acquiring bandits

0 references

Q3221798

0 references

Q3815845

0 references

Open Bandit Processes with Uncountable States and Time-Backward Effects

0 references

Identifiers

Mathematics Subject Classification ID

0 references

0 references

0 references

10.1016/J.CSDA.2022.107610

0 references

Sitelinks

Mathematics(1 entry)

mardi Publication:6167036

@@ Property / DOI @@
-.1016/j.csda.2022.107610
@@ Property / DOI: 10.1016/j.csda.2022.107610 / rank @@
-Normal rank
@@ Property / cites work @@
+Sample mean based index policies by <i>O</i>(log <i>n</i>) regret for the multi-armed bandit problem
+Normal rank
@@ Property / cites work @@
+Finite-time analysis of the multiarmed bandit problem
+Normal rank
@@ Property / cites work @@
+Q4998881
@@ Property / cites work: Q4998881 / rank @@
+Normal rank
@@ Property / cites work @@
+Methods and Applications of Statistics in Clinical Trials
+Normal rank
@@ Property / cites work @@
+On Gittins' index theorem in continuous time
@@ Property / cites work: On Gittins' index theorem in continuous time / rank @@
+Normal rank
@@ Property / cites work @@
+A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches
+Normal rank
@@ Property / cites work @@
+Optimal stochastic scheduling
@@ Property / cites work: Optimal stochastic scheduling / rank @@
+Normal rank
@@ Property / cites work @@
+On the Whittle index of Markov modulated restless bandits
+Normal rank
@@ Property / cites work @@
+General Gittins index processes in discrete time.
@@ Property / cites work: General Gittins index processes in discrete time. / rank @@
+Normal rank
@@ Property / cites work @@
+Dynamic allocation problems in continuous time
@@ Property / cites work: Dynamic allocation problems in continuous time / rank @@
+Normal rank
@@ Property / cites work @@
+Synchronization and optimality for multi-armed bandit problems in continuous time
+Normal rank
@@ Property / cites work @@
+Continuous-time allocation indices and their discrete-time approximation
+Normal rank
@@ Property / cites work @@
+Consistency of Sequential Bayesian Sampling Policies
+Normal rank
@@ Property / cites work @@
+Q4197923
@@ Property / cites work: Q4197923 / rank @@
+Normal rank
@@ Property / cites work @@
+Q4057976
@@ Property / cites work: Q4057976 / rank @@
+Normal rank
@@ Property / cites work @@
+On Bayesian models in stochastic scheduling
@@ Property / cites work: On Bayesian models in stochastic scheduling / rank @@
+Normal rank
@@ Property / cites work @@
+Q4692329
@@ Property / cites work: Q4692329 / rank @@
+Normal rank
@@ Property / cites work @@
+Multi‐Armed Bandit Allocation Indices
@@ Property / cites work: Multi‐Armed Bandit Allocation Indices / rank @@
+Normal rank
@@ Property / cites work @@
+Multi-armed bandit problem revisited
@@ Property / cites work: Multi-armed bandit problem revisited / rank @@
+Normal rank
@@ Property / cites work @@
+Gittins indices in the dynamic allocation problem for diffusion processes
+Normal rank
@@ Property / cites work @@
+Lévy bandits: Multi-armed bandits driven by Lévy processes
+Normal rank
@@ Property / cites work @@
+Multi-armed bandits in discrete and continuous time
+Normal rank
@@ Property / cites work @@
+On Bayesian index policies for sequential resource allocation
+Normal rank
@@ Property / cites work @@
+A Survey of Some Results in Stochastic Adaptive Control
+Normal rank
@@ Property / cites work @@
+Asymptotically efficient adaptive allocation rules
+Normal rank
@@ Property / cites work @@
+Open bandit processes and optimal scheduling of queueing networks
+Normal rank
@@ Property / cites work @@
+Adaptive treatment allocation and the multi-armed bandit problem
+Normal rank
@@ Property / cites work @@
+The Multi-Armed Bandit With Stochastic Plays
@@ Property / cites work: The Multi-Armed Bandit With Stochastic Plays / rank @@
+Normal rank
@@ Property / cites work @@
+ON THE OPTIMALITY OF AN INDEX RULE IN MULTICHANNEL ALLOCATION  FOR SINGLE-HOP MOBILE NETWORKS WITH MULTIPLE SERVICE CLASSES
+Normal rank
@@ Property / cites work @@
+Bandit Algorithms
@@ Property / cites work: Bandit Algorithms / rank @@
+Normal rank
@@ Property / cites work @@
+On the Whittle Index for Restless Multiarmed Hidden Markov Bandits
+Normal rank
@@ Property / cites work @@
+A minimax and asymptotically optimal algorithm for stochastic bandits
+Normal rank
@@ Property / cites work @@
+Dynamic priority allocation via restless bandit marginal productivity indices
+Normal rank
@@ Property / cites work @@
+Some aspects of the sequential design of experiments
+Normal rank
@@ Property / cites work @@
+Linearly Parameterized Bandits
@@ Property / cites work: Linearly Parameterized Bandits / rank @@
+Normal rank
@@ Property / cites work @@
+Q4626283
@@ Property / cites work: Q4626283 / rank @@
+Normal rank
@@ Property / cites work @@
+A short proof of the Gittins index theorem
@@ Property / cites work: A short proof of the Gittins index theorem / rank @@
+Normal rank
@@ Property / cites work @@
+Extensions of the multiarmed bandit problem: The discounted case
+Normal rank
@@ Property / cites work @@
+INDEXABILITY AND OPTIMAL INDEX POLICIES FOR A CLASS OF REINITIALISING RESTLESS BANDITS
+Normal rank
@@ Property / cites work @@
+Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
+Normal rank
@@ Property / cites work @@
+On the Gittins index for multiarmed bandits
@@ Property / cites work: On the Gittins index for multiarmed bandits / rank @@
+Normal rank
@@ Property / cites work @@
+Branching Bandit Processes
@@ Property / cites work: Branching Bandit Processes / rank @@
+Normal rank
@@ Property / cites work @@
+Q3882215
@@ Property / cites work: Q3882215 / rank @@
+Normal rank
@@ Property / cites work @@
+Arm-acquiring bandits
@@ Property / cites work: Arm-acquiring bandits / rank @@
+Normal rank
@@ Property / cites work @@
+Q3221798
@@ Property / cites work: Q3221798 / rank @@
+Normal rank
@@ Property / cites work @@
+Q3815845
@@ Property / cites work: Q3815845 / rank @@
+Normal rank
@@ Property / cites work @@
+Open Bandit Processes with Uncountable States and Time-Backward Effects
+Normal rank
@@ Property / DOI @@
+.1016/J.CSDA.2022.107610
@@ Property / DOI: 10.1016/J.CSDA.2022.107610 / rank @@
+Normal rank