File(s) under permanent embargo
Potential-based multiobjective reinforcement learning approaches to low-impact agents for AI safety
journal contribution
posted on 2021-04-01, 00:00 authored by P Vamplew, C Foale, Richard DazeleyRichard Dazeley, A BignoldPotential-based multiobjective reinforcement learning approaches to low-impact agents for AI safety
History
Journal
Engineering Applications of Artificial IntelligenceVolume
100Article number
104186Pagination
1 - 16Location
Amsterdam, The NetherlandsPublisher DOI
ISSN
0952-1976eISSN
1873-6769Language
EnglishPublication classification
C1 Refereed article in a scholarly journalPublisher
PERGAMON-ELSEVIER SCIENCE LTDUsage metrics
Categories
No categories selectedKeywords
Science & TechnologyTechnologyAutomation & Control SystemsComputer Science, Artificial IntelligenceEngineering, MultidisciplinaryEngineering, Electrical & ElectronicComputer ScienceEngineeringSafe reinforcement learningMultiobjective reinforcement learningAI safetyPotential-based rewardsLow-impact agentsReward engineeringSide-effects4602 Artificial intelligence
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC