Regret in the on-line decision problem (Q1818283): Difference between revisions

From MaRDI portal
Importer (talk | contribs)
Created a new Item
 
Import241208061232 (talk | contribs)
Normalize DOI.
 
(5 intermediate revisions by 5 users not shown)
Property / DOI
 
Property / DOI: 10.1006/game.1999.0740 / rank
Normal rank
 
Property / describes a project that uses
 
Property / describes a project that uses: AdaBoost.MH / rank
 
Normal rank
Property / MaRDI profile type
 
Property / MaRDI profile type: MaRDI publication profile / rank
 
Normal rank
Property / OpenAlex ID
 
Property / OpenAlex ID: W2135730283 / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q4252717 / rank
 
Normal rank
Property / cites work
 
Property / cites work: On Pseudo-Games / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3234879 / rank
 
Normal rank
Property / cites work
 
Property / cites work: An analog of the minimax theorem for vector payoffs / rank
 
Normal rank
Property / cites work
 
Property / cites work: How to use expert advice / rank
 
Normal rank
Property / cites work
 
Property / cites work: Universal Portfolios / rank
 
Normal rank
Property / cites work
 
Property / cites work: Choice Without Beliefs / rank
 
Normal rank
Property / cites work
 
Property / cites work: Universal prediction of individual sequences / rank
 
Normal rank
Property / cites work
 
Property / cites work: Prediction in the worst case / rank
 
Normal rank
Property / cites work
 
Property / cites work: A Randomization Rule for Selecting Forecasts / rank
 
Normal rank
Property / cites work
 
Property / cites work: Asymptotic calibration / rank
 
Normal rank
Property / cites work
 
Property / cites work: Calibrated learning and correlated equilibrium / rank
 
Normal rank
Property / cites work
 
Property / cites work: Consistency and cautious fictitious play / rank
 
Normal rank
Property / cites work
 
Property / cites work: An easier way to calibrate. / rank
 
Normal rank
Property / cites work
 
Property / cites work: Conditional universal consistency. / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3245635 / rank
 
Normal rank
Property / cites work
 
Property / cites work: A Simple Adaptive Procedure Leading to Correlated Equilibrium / rank
 
Normal rank
Property / cites work
 
Property / cites work: Q3002852 / rank
 
Normal rank
Property / cites work
 
Property / cites work: The weighted majority algorithm / rank
 
Normal rank
Property / cites work
 
Property / cites work: On repeated games with incomplete information played by non-Bayesian players / rank
 
Normal rank
Property / cites work
 
Property / cites work: Weak Approachability / rank
 
Normal rank
Property / DOI
 
Property / DOI: 10.1006/GAME.1999.0740 / rank
 
Normal rank
links / mardi / namelinks / mardi / name
 

Latest revision as of 10:01, 16 December 2024

scientific article
Language Label Description Also known as
English
Regret in the on-line decision problem
scientific article

    Statements

    Regret in the on-line decision problem (English)
    0 references
    0 references
    0 references
    2 May 2001
    0 references
    The paper deals with a specific type of the decision making sequences. It assumed that a decision-maker makes a time sequence of decisions, and his final loss depends on the accepted decision as well as on the actual state of the world. Moreover, in the time of the decision making the agent has no information about the state of the world. His aim is to minimize the total loss. A basic concept of the presented model is the one of the ``regret'' which characterizes the difference between the loss following after some decision, and the expected loss connected with an alternative decision making strategy. The main results formulate the properties of the regret and its relation to the optimal decision making.
    0 references
    0 references
    uncertaint
    0 references
    regret
    0 references
    decision making
    0 references
    actual state of the world
    0 references

    Identifiers