Online Regret Bounds for Undiscounted Continuous Reinforcement Learning

Ronald Ortner 1 Daniil Ryabko 2
1 MUL - Montanuniversität Leoben
2 SEQUEL - Sequential Learning
LIFL - Laboratoire d'Informatique Fondamentale de Lille, Inria Lille - Nord Europe, LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Document type :
Conference papers
Complete list of metadatas
https://hal.inria.fr/hal-00765441
Contributor : Daniil Ryabko <>
Submitted on : Friday, December 14, 2012 - 3:59:32 PM
Last modification on : Thursday, February 21, 2019 - 10:52:49 AM

Identifiers

  • HAL Id : hal-00765441, version 1

Collections

CNRS | INRIA | UNIV-LILLE3 | LAGIS

Citation

Ronald Ortner, Daniil Ryabko. Online Regret Bounds for Undiscounted Continuous Reinforcement Learning. NIPS 2012, 2012, Lake Tahoe, United States. pp.1772--1780. ⟨hal-00765441⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

4452

 

 

Contact

archive-ouverte@inria.fr