Publication:

No more hand-tuning rewards: Masked constrained policy optimization for safe reinforcement learning

Date

2021
Proceedings Paper
Simple item page Full metadata Statistics
 
dc.contributor.authorVan Havermaet, Stef
dc.contributor.authorKhaluf, Yara
dc.contributor.authorSimoens, Pieter
dc.contributor.imecauthorVan Havermaet, Stef
dc.contributor.imecauthorKhaluf, Yara
dc.contributor.imecauthorSimoens, Pieter
dc.contributor.orcidimecSimoens, Pieter::0000-0002-9569-9373
dc.date.accessioned2021-10-31T12:02:30Z
dc.date.available2021-10-31T12:02:30Z
dc.date.embargo9999-12-31
dc.date.issued2021
dc.identifier.urihttps://imec-publications.be/handle/20.500.12860/37290
dc.identifier.urlhttp://www.ifaamas.org/Proceedings/aamas2021/pdfs/p1344.pdf
dc.source.beginpage1344
dc.source.conferenceAAMAS2021, the 20th International Conference on Autonomous Agents and Multiagent Systems
dc.source.conferencedate3/05/2021
dc.source.conferencelocationOnline Online
dc.source.endpage1352
dc.title

No more hand-tuning rewards: Masked constrained policy optimization for safe reinforcement learning

dc.typeProceedings paper
dspace.entity.typePublication
Files

Original bundle

Name:
48442.pdf
Size:
1.38 MB
Format:
Adobe Portable Document Format
Download
Publication available in collections:
Conference contributions