Performance bound for Approximate Optimistic Policy Iteration

Bruno Scherrer 1 Christophe Thiery 1
1 MAIA - Autonomous intelligent machine
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We provide a proof of the performance bound theorem published in "Least-Squares λ Policy Iteration: Bias-Variance Trade-off in Control Problems" (ICML 2010).
Document type :
Reports
Complete list of metadatas

https://hal.inria.fr/inria-00480952
Contributor : Christophe Thiery <>
Submitted on : Wednesday, May 5, 2010 - 2:56:27 PM
Last modification on : Thursday, January 11, 2018 - 6:19:51 AM
Long-term archiving on : Thursday, September 16, 2010 - 1:36:05 PM

File

opi_proof.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00480952, version 1

Collections

Citation

Bruno Scherrer, Christophe Thiery. Performance bound for Approximate Optimistic Policy Iteration. [Technical Report] 2010. ⟨inria-00480952⟩

Share

Metrics

Record views

395

Files downloads

279