Show simple item record

dc.contributor.authorMahony, Amanda
dc.date.accessioned2019-06-25T23:30:39Z
dc.date.available2019-06-25T23:30:39Z
dc.date.issued2018
dc.identifier.isbn978-3-030-02449-9
dc.identifier.issn0302-9743
dc.identifier.doi10.1007/978-3-030-02450-5_37
dc.identifier.urihttp://hdl.handle.net/10072/385797
dc.description.abstractReinforcement learning has had great empirical success in different domains, which has left theoretical foundations, such as performance guarantees, lagging behind. The usual asymptotic convergence to an optimal policy is not strong enough for applications in the real world. Meta learning algorithms aim to use experience from multiple tasks to increase performance on all tasks individually and decrease time taken to reach an acceptable policy. This paper proposes to study the provable properties of meta-reinforcement learning.
dc.description.peerreviewedYes
dc.publisherSpringer Nature
dc.publisher.placeSwitzerland
dc.relation.ispartofconferencenameICFEM 2018
dc.relation.ispartofconferencetitleLecture Notes in Computer Science
dc.relation.ispartofdatefrom2018-11-12
dc.relation.ispartofdateto2016-11-16
dc.relation.ispartoflocationGold Coast, Australia
dc.relation.ispartofpagefrom469
dc.relation.ispartofpageto472
dc.relation.ispartofvolume11232
dc.subject.fieldofresearchElectrical and Electronic Engineering
dc.subject.fieldofresearchInformation and Computing Sciences
dc.subject.fieldofresearchcode0906
dc.subject.fieldofresearchcode08
dc.titleFormalising performance guarantees in meta-reinforcement learning
dc.typeConference output
dc.type.descriptionE1 - Conferences
dc.type.codeE - Conference Publications
gro.hasfulltextNo Full Text
gro.griffith.authorMahony, Amanda


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

  • Conference outputs
    Contains papers delivered by Griffith authors at national and international conferences.

Show simple item record