Hierarchical policy network

 |  Login

Show simple item record

dc.contributor Aalto-yliopisto fi
dc.contributor Aalto University en
dc.contributor.advisor Berglund, Mathias
dc.contributor.author Koppali, Eva
dc.date.accessioned 2018-06-29T08:41:23Z
dc.date.available 2018-06-29T08:41:23Z
dc.date.issued 2018-06-18
dc.identifier.uri https://aaltodoc.aalto.fi/handle/123456789/32383
dc.description.abstract Ability to learn effective policies from control examples is an apparent milestone towards expert and general artificial intelligences. Methodology for developing this ability have taken a new turn with incorporating deep learning in the classic control setting. However, conventional methods face a few challenges, the most severe of which is the adversarial behavior problem. To address the challenges, this thesis examines mechanics of neural networks leading to the undesired effects, and discusses existing and new solutions. In particular, this thesis studies how adversarial effects can be countered with denoising-based methods. For this purpose, the study has developed a simulation environment from which a dataset was collected, and world models were approximated from the dataset in offline fashion. Then, for demonstrating the adversarial behavior problem as well as proposed solution in domain of control setting, a proxy MPC-based application was developed. Finally, experiments with an aggregated policy network revealed additional challenges related to inaccuracies of trajectories simulated during the training, and insufficient coverage of the training manifold during the optimization process. These problems were addressed with development of auxiliary techniques. The results of the theoretical and experimental study indicate that the primary task of policy acquisition is prone to adversarial and similar effects, which are reviewed as natural phenomena occurring in all neural networks, and that denoising-based methods can be successfully utilized as a countermeasure. The thesis assesses effectiveness and limitations of employed methods. en
dc.format.extent 118
dc.language.iso en en
dc.title Hierarchical policy network en
dc.type G2 Pro gradu, diplomityö fi
dc.contributor.school Sähkötekniikan korkeakoulu fi
dc.subject.keyword adversarial effects en
dc.subject.keyword policy network en
dc.subject.keyword offline predictive model en
dc.subject.keyword policy optimization en
dc.identifier.urn URN:NBN:fi:aalto-201806293793
dc.programme.major Control, Robotics and Autonomous Systems fi
dc.programme.mcode ELEC3025 fi
dc.type.ontasot Master's thesis en
dc.type.ontasot Diplomityö fi
dc.contributor.supervisor Kyrki, Ville
dc.programme AEE - Master’s Programme in Automation and Electrical Engineering (TS2013) fi
dc.location P1 fi
local.aalto.electroniconly yes
local.aalto.openaccess no


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search archive


Advanced Search

article-iconSubmit a publication

Browse

My Account