Exploration Strategies for Homeostatic Agents: Continuous and dynamic exploration for homeostatic regulation using deep reinforcement learning

Visa enkel post
dc.contributor.authorAndersson, Patrick
dc.contributor.authorStrandman, Anton
dc.contributor.departmentChalmers tekniska högskola / Institutionen för data och informationstekniksv
dc.contributor.examinerHaghir Chehreghani, Morteza
dc.contributor.supervisorStrannegård, Claes
dc.date.accessioned2019-07-19T09:35:05Z
dc.date.available2019-07-19T09:35:05Z
dc.date.issued2019sv
dc.date.submitted2019
dc.description.abstractThis paper introduces and evaluates four novel exploration strategies for homeostatic agents. Homeostatic agents have the objective of keeping some internal variables as close to a predetermined optimum as possible. Reinforcement learning is used for decision making, and the agents are given access to the optimal and acceptable values of the internal variables, giving greater flexibility for exploration and better survival chances. The new exploration strategies that utilise the internal variables are evaluated in a range of environments, showing them to outperform common reinforcement learning exploration techniques where these variables are not taken into consideration.sv
dc.identifier.coursecodeDATX05sv
dc.identifier.urihttps://hdl.handle.net/20.500.12380/300061
dc.language.isoengsv
dc.setspec.uppsokTechnology
dc.subjectartificial general intelligencesv
dc.subjectmulti-objective reinforcement learningsv
dc.subjectexplorationsv
dc.subjecthomeostatic regulationsv
dc.subjectanimatsv
dc.subjecthomeostatic explorationsv
dc.titleExploration Strategies for Homeostatic Agents: Continuous and dynamic exploration for homeostatic regulation using deep reinforcement learningsv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
CSE 19-58 Andersson_Strandman.pdf
Storlek:
30.12 MB
Format:
Adobe Portable Document Format
Beskrivning:
Exploration Strategies for Homeostatic Agents: Continuous and dynamic exploration for homeostatic regulation using deep reinforcement learning
Ladda ner
License bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
license.txt
Storlek:
1.14 KB
Format:
Item-specific license agreed upon to submission
Beskrivning:
Ladda ner
Samling
Examensarbeten för masterexamen