Work

Optimistic linear programming gives logarithmic regret for irreducible MDPs

Year: 2007

Type: conference-paper

Source: QUT ePrints (Queensland University of Technology)

Authors: Ambuj Tewari, Peter L. Bartlett

Institution: University of California, Berkeley

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: closed

OpenAlex ID: W1496720559

FWCI: 4.457

Cites:

Cited by: 40

Related to: 10