Advantage Based Value Iteration for Markov Decision Processes with Unknown Rewards

Pegah Alizadeh 1 Yann Chevaleyre 1 François Lévy 2
2 RCLN
LIPN - Laboratoire d'Informatique de Paris-Nord
Document type :
Conference papers
Complete list of metadatas

https://hal-auf.archives-ouvertes.fr/hal-01358345
Contributor : François Lévy <>
Submitted on : Wednesday, August 31, 2016 - 3:19:17 PM
Last modification on : Wednesday, February 6, 2019 - 1:23:38 AM

Identifiers

  • HAL Id : hal-01358345, version 1

Collections

Citation

Pegah Alizadeh, Yann Chevaleyre, François Lévy. Advantage Based Value Iteration for Markov Decision Processes with Unknown Rewards. International Joint Conference on Neural Networks (IJCNN 2016), Jul 2016, Vancouver, Canada. ⟨hal-01358345⟩

Share

Metrics

Record views

341