OpenAlex
PricingAboutJobs
Log inGet started
Work

Logarithmic Online Regret Bounds for Undiscounted Reinforcement Learning

HTML

Year: 2007
Type: book-chapter
Source: The MIT Press eBooks
Parent work: Advances in Neural Information Processing Systems 19: Proceedings of the 2006 Conference
DOI: 10.7551/mitpress/7503.003.0011
Authors: Peter Auer, Ronald Ortner
Institution: Montanuniversität Leoben
Language: English

Topic: Advanced Bandit Algorithms Research
Subfield: Management Science and Operations Research
Field: Decision Sciences
Domain: Social Sciences
Keywords: exploration-exploitation balance, multi-armed bandits, logarithmic regret, optimal policy

Open Access status: closed

Funder: Austrian Science Fund
Award: Computer Models for Biological Vision Systems
OpenAlex ID: W2097931172
FWCI: 23.7
Cites: 18
Cited by: 232
Related to: 10
OpenAlex
Nonprofit
Open DataOpen Data
Open Source
Product
Search
Compare
Pricing
Repositories
Unpaywall
Unsub
Developers
API docs
Data snapshot
Status
Source code
Organization
About
Team
Testimonials
Brand
Jobs
Community
Help center
Contact
Events
Blog
Mailing list
Subscribe
Supporters
Legal
Privacy
Accessibility
Terms
Security