Inverse Reinforcement Learning in Relational Domains

Abstract : In this work, we introduce the first approach to the Inverse Reinforcement Learning (IRL) problem in relational domains. IRL has been used to recover a more compact representation of the expert policy leading to better generalization performances among different contexts. On the other hand, rela-tional learning allows representing problems with a varying number of objects (potentially infinite), thus provides more generalizable representations of problems and skills. We show how these different formalisms allow one to create a new IRL algorithm for relational domains that can recover with great efficiency rewards from expert data that have strong generalization and transfer properties. We evaluate our algorithm in representative tasks and study the impact of diverse experimental conditions such as : the number of demonstrations, knowledge about the dynamics, transfer among varying dimensions of a problem, and changing dynamics.
Complete list of metadatas

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01154650
Contributor : Thiabut Munzer <>
Submitted on : Friday, May 22, 2015 - 4:08:27 PM
Last modification on : Wednesday, July 3, 2019 - 10:48:04 AM
Long-term archiving on : Thursday, April 20, 2017 - 7:26:24 AM

File

IJCAI2015_HAL.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01154650, version 1

Citation

Thibaut Munzer, Bilal Piot, Matthieu Geist, Olivier Pietquin, Manuel Lopes. Inverse Reinforcement Learning in Relational Domains. International Joint Conferences on Artificial Intelligence, Jul 2015, Buenos Aires, Argentina. ⟨hal-01154650⟩

Share

Metrics

Record views

1402

Files downloads

547