Advanced Search
DSpace@MIT

Learning Models of Sequential Decision-Making without Complete State Specification using Bayesian Nonparametric Inference and Active Querying

Research and Teaching Output of the MIT Community

Show simple item record

dc.contributor.advisor Julie A Shah
dc.contributor.author Unhelkar, Vaibhav V. en_US
dc.contributor.author Shah, Julie A. en_US
dc.contributor.other Interactive Robotics Group en
dc.date.accessioned 2018-05-17T19:19:11Z
dc.date.available 2018-05-17T19:19:11Z
dc.date.issued 2018-05-17
dc.identifier.uri http://hdl.handle.net/1721.1/115482
dc.description.abstract Learning models of decision-making behavior during sequential tasks is useful across a variety of applications, including human-machine interaction. In this paper, we present an approach to learning such models within Markovian domains based on observing and querying a decision-making agent. In contrast to classical approaches to behavior learning, we do not assume complete knowledge of the state features that impact an agent's decisions. Using tools from Bayesian nonparametric inference and time series of agents decisions, we first provide an inference algorithm to identify the presence of any unmodeled state features that impact decision making, as well as likely candidate models. In order to identify the best model among these candidates, we next provide an active querying approach that resolves model ambiguity by querying the decision maker. Results from our evaluations demonstrate that, using the proposed algorithms, an observer can identify the presence of latent state features, recover their dynamics, and estimate their impact on decisions during sequential tasks. en_US
dc.format.extent 11 p. en_US
dc.relation.ispartofseries MIT-CSAIL-TR-2018-015
dc.subject Decision Making, Graphical Models, Human-AI Collaboration en_US
dc.title Learning Models of Sequential Decision-Making without Complete State Specification using Bayesian Nonparametric Inference and Active Querying en_US
dc.date.updated 2018-05-17T19:19:11Z


Files in this item

Name Size Format Description
MIT-CSAIL-TR-2018 ... 238.6Kb PDF

This item appears in the following Collection(s)

Show simple item record

MIT-Mirage