Learning to Play Games from Multiple Imperfect Teachers

Visa enkel post
dc.contributor.authorKarlsson, John
dc.contributor.departmentChalmers tekniska högskola / Institutionen för data- och informationsteknik (Chalmers)sv
dc.contributor.departmentChalmers University of Technology / Department of Computer Science and Engineering (Chalmers)en
dc.date.accessioned2019-07-03T13:30:51Z
dc.date.available2019-07-03T13:30:51Z
dc.date.issued2014
dc.description.abstractThis project evaluates the modularity of a recent Bayesian Inverse Reinforcement Learning approach [1] by inferring the sub-goals correlated with winning board games from observations of a set of agents. A feature based architecture is proposed together with a method for generating the reward function space, making inference tractable in large state spaces and allowing for the combination with models that approximate stateaction values. Further, a policy prior is suggested that allows for least squares policy evaluation using sample trajectories. The model is evaluated on randomly generated environments and on Tic-tac-toe, showing that a combination of the intentions inferred from all agents can generate strategies that outperform the corresponding strategies from each individual agent.
dc.identifier.urihttps://hdl.handle.net/20.500.12380/203067
dc.language.isoeng
dc.setspec.uppsokTechnology
dc.subjectData- och informationsvetenskap
dc.subjectComputer and Information Science
dc.titleLearning to Play Games from Multiple Imperfect Teachers
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster Thesisen
dc.type.uppsokH
local.programmeComplex adaptive systems (MPCAS), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
203067.pdf
Storlek:
595.92 KB
Format:
Adobe Portable Document Format
Beskrivning:
Fulltext
Ladda ner
Samling
Examensarbeten för masterexamen