Whittle index
E695660
heuristic
index policy
policy for restless multi-armed bandits
solution concept in stochastic control
The Whittle index is a heuristic index policy in stochastic control and multi-armed bandit problems that provides a tractable way to make near-optimal sequential decisions under uncertainty.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Whittle index canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T7853035 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Whittle index Context triple: [Peter Whittle, knownFor, Whittle index]
-
A.
Foundations of a General Theory of Sequential Decision Functions
Foundations of a General Theory of Sequential Decision Functions is a seminal work in statistics that established the mathematical foundations of sequential analysis and optimal decision-making under uncertainty.
-
B.
Introduction to Stochastic Control Theory
Introduction to Stochastic Control Theory is a foundational textbook that systematically develops the theory and methods for controlling dynamical systems under uncertainty using probabilistic and stochastic-process tools.
-
C.
Snell envelope
The Snell envelope is a stochastic process that represents the smallest supermartingale dominating a given process and is fundamental in optimal stopping theory and the valuation of American-style options.
-
D.
Khinchin–Pollaczek formula
The Khinchin–Pollaczek formula is a result in probability theory and queueing theory that provides an explicit expression for the stationary waiting-time distribution in certain single-server queues.
-
E.
Statistical Decision Functions
Statistical Decision Functions is a foundational work in decision theory and statistics that systematically develops the theory of optimal decision-making under uncertainty.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Whittle index Target entity description: The Whittle index is a heuristic index policy in stochastic control and multi-armed bandit problems that provides a tractable way to make near-optimal sequential decisions under uncertainty.
-
A.
Foundations of a General Theory of Sequential Decision Functions
Foundations of a General Theory of Sequential Decision Functions is a seminal work in statistics that established the mathematical foundations of sequential analysis and optimal decision-making under uncertainty.
-
B.
Introduction to Stochastic Control Theory
Introduction to Stochastic Control Theory is a foundational textbook that systematically develops the theory and methods for controlling dynamical systems under uncertainty using probabilistic and stochastic-process tools.
-
C.
Snell envelope
The Snell envelope is a stochastic process that represents the smallest supermartingale dominating a given process and is fundamental in optimal stopping theory and the valuation of American-style options.
-
D.
Khinchin–Pollaczek formula
The Khinchin–Pollaczek formula is a result in probability theory and queueing theory that provides an explicit expression for the stationary waiting-time distribution in certain single-server queues.
-
E.
Statistical Decision Functions
Statistical Decision Functions is a foundational work in decision theory and statistics that systematically develops the theory of optimal decision-making under uncertainty.
- F. None of above. chosen
Statements (48)
| Predicate | Object |
|---|---|
| instanceOf |
heuristic
ⓘ
index policy ⓘ policy for restless multi-armed bandits ⓘ solution concept in stochastic control ⓘ |
| appliesTo | restless bandit with subsidy for passivity formulation ⓘ |
| approximationType | asymptotically optimal in some regimes ⓘ |
| characteristic |
computationally tractable
ⓘ
decentralized decision rule ⓘ heuristically near-optimal ⓘ indexability-based ⓘ state-dependent priority index ⓘ |
| comparedTo | Gittins index ⓘ |
| decisionRule | activate arms with largest indices ⓘ |
| definedFor |
each arm in a restless bandit
ⓘ
each state of an arm ⓘ |
| differsFrom | Gittins index for classic bandits ⓘ |
| field |
applied probability
ⓘ
control theory ⓘ operations research ⓘ reinforcement learning ⓘ stochastic processes ⓘ |
| generalizes | index policies to restless bandits ⓘ |
| hasLimitation |
computation can be complex for high-dimensional states
ⓘ
may be suboptimal when indexability fails ⓘ |
| introducedBy | Peter Whittle ⓘ |
| introducedIn | restless bandit literature of the 1980s ⓘ |
| namedAfter | Peter Whittle ⓘ |
| optimizes |
discounted reward approximately
ⓘ
long-run average reward approximately ⓘ |
| requires |
indexability condition
ⓘ
solution of single-project dynamic program ⓘ |
| usedFor |
large-scale dynamic allocation problems
ⓘ
near-optimal sequential decision making ⓘ |
| usedIn |
communication networks
ⓘ
dynamic resource allocation ⓘ dynamic spectrum allocation ⓘ healthcare resource allocation ⓘ inventory control ⓘ machine maintenance problems ⓘ multi-armed bandit problems ⓘ operations research ⓘ opportunistic spectrum access ⓘ queueing systems ⓘ restless bandit problems ⓘ scheduling problems ⓘ sensor scheduling ⓘ sequential decision making under uncertainty ⓘ stochastic control ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Whittle index Description of subject: The Whittle index is a heuristic index policy in stochastic control and multi-armed bandit problems that provides a tractable way to make near-optimal sequential decisions under uncertainty.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.