Autonomous Driving: A Multi-Objective Deep Reinforcement Learning Approach

dc.contributor.authorLi, Changjian
dc.date.accessioned2019-05-23T17:55:00Z
dc.date.available2019-05-23T17:55:00Z
dc.date.issued2019-05-23
dc.date.submitted2019-05-17
dc.description.abstractAutonomous driving is a challenging domain that entails multiple aspects: a vehicle should be able to drive to its destination as fast as possible while avoiding collision, obeying traffic rules and ensuring the comfort of passengers. It's representative of complex reinforcement learning tasks humans encounter in real life. The aim of this thesis is to explore the effectiveness of multi-objective reinforcement learning for such tasks characterized by autonomous driving. In particular, it shows that: 1. Multi-objective reinforcement learning is effective at overcoming some of the difficulties faced by scalar-reward reinforcement learning, and a multi-objective DQN agent based on a variant of thresholded lexicographic Q-learning is successfully trained to drive on multi-lane roads and intersections, yielding and changing lanes according to traffic rules. 2. Data efficiency of (multi-objective) reinforcement learning can be significantly improved by exploiting the factored structure of a task. Specifically, factored Q functions learned on the factored state space can be used as features to the original Q function to speed up learning. 3. Inclusion of history-dependent policies enables an intuitive exact algorithm for multi-objective reinforcement learning with thresholded lexicographic order.en
dc.identifier.urihttp://hdl.handle.net/10012/14697
dc.language.isoenen
dc.pendingfalse
dc.publisherUniversity of Waterlooen
dc.subjectautonomous drivingen
dc.subjectreinforcement learningen
dc.subjectMarkov decision processen
dc.subjectdeep learningen
dc.titleAutonomous Driving: A Multi-Objective Deep Reinforcement Learning Approachen
dc.typeMaster Thesisen
uws-etd.degreeMaster of Applied Scienceen
uws-etd.degree.departmentElectrical and Computer Engineeringen
uws-etd.degree.disciplineElectrical and Computer Engineeringen
uws-etd.degree.grantorUniversity of Waterlooen
uws.contributor.advisorCzarnecki, Krzysztof
uws.contributor.affiliation1Faculty of Engineeringen
uws.peerReviewStatusUnrevieweden
uws.published.cityWaterlooen
uws.published.countryCanadaen
uws.published.provinceOntarioen
uws.scholarLevelGraduateen
uws.typeOfResourceTexten

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Li_Changjian.pdf
Size:
921.63 KB
Format:
Adobe Portable Document Format
Description:

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
6.08 KB
Format:
Item-specific license agreed upon to submission
Description: