Dynamic Network Architectures for Deep Q-Learning: Modelling Neurogenesis in Artificial Intelligence

dc.contributor.authorEriksson, Pontus
dc.contributor.authorWestlund Gotby, Love
dc.contributor.departmentChalmers tekniska högskola / Institutionen för data och informationstekniksv
dc.contributor.examinerHaghir Chehreghani, Morteza
dc.contributor.supervisorStrannegård, Claes
dc.date.accessioned2019-07-19T08:25:43Z
dc.date.available2019-07-19T08:25:43Z
dc.date.issued2019sv
dc.date.submitted2019
dc.description.abstractArtificial neural networks have become popular within a range of machine learning fields for their ability to solve complex problems, with one of the uses as function approximators in Q-learning. These networks generally have static architectures, which is a problem in the regard of artificial general intelligence, since no single specific architecture is optimal for all problems. In this thesis, we implement and evaluate a proof of concept for a novel approach of a dynamic network architecture, resulting in a model that can be seen as a combination of compressed classical table-based Q-learning and artificial neural networks. The model presented performs true tabula rasa deep Q-learning, starting with an empty network that is gradually extended with nodes when experiencing “surprising” events, and is capable of generalization by abstracting important features from noisy input. Finally, we show that the model can learn from delayed rewards in simple environments and compare it with the well-established DQN algorithm.sv
dc.identifier.coursecodeDATX05sv
dc.identifier.urihttps://hdl.handle.net/20.500.12380/300056
dc.language.isoengsv
dc.setspec.uppsokTechnology
dc.subjectdynamic neural networksv
dc.subjectartificial neural networksv
dc.subjectANNsv
dc.subjectQ-learningsv
dc.subjectDQNsv
dc.subjectdeep learningsv
dc.subjectmachine learningsv
dc.subjectreinforcement learningsv
dc.titleDynamic Network Architectures for Deep Q-Learning: Modelling Neurogenesis in Artificial Intelligencesv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
CSE 19-48 Westlund Gotby Eriksson.pdf
Storlek:
1.7 MB
Format:
Adobe Portable Document Format
Beskrivning:
Dynamic Network Architectures for Deep Q-Learning: Modelling Neurogenesis in Artificial Intelligence
License bundle
Visar 1 - 1 av 1
Bild saknas
Namn:
license.txt
Storlek:
1.14 KB
Format:
Item-specific license agreed upon to submission
Beskrivning: