Objective Decision-theoretic sequential decision making (SDM) is concerned with endowing an intelligent agent with the capability to choose actions that optimize task performance. SDM techniques have the potential to revolutionize many aspects of society and recent successes, e.g. agents that play Atari games and beat a world champion in the game of Go, have sparked renewed interest in this field.However, despite these successes, fundamental problems of scalability prevents these methods from addressing other problems with hundreds or thousands of state variables. For instance, there is no principled way of computing an optimal or near-optimal traffic light control plan for an intersection that takes into account the current state of traffic in an entire city. I will develop one in this project.To achieve this, I will develop a new class of influence-based SDM methods that overcome scalability issues for such problems by using novel ways of abstraction. Considered from a decentralized system perspective, the intersection’s local problem is manageable, but the influence that the rest of the network exerts on it is complex. The key idea is that by using (deep) machine learning methods, we can learn sufficiently accurate representations of such influence to facilitate near-optimal decisions.This project will construct a theoretical framework for such approximate influence representations and SDM methods that use them. Scalability of these methods will be demonstrated by rigorous empirical evaluation on two simulated challenge domains: traffic lights control in an entire city, and robotic order picking in a large-scale autonomous warehouse.If successful, INFLUENCE will produce a range of influence-based SDM algorithms that can, in a principled manner, deal with a broad range of very large complex problems consisting of hundreds or thousands of variables, thus making an important step towards realizing the promise of autonomous agent technology. Fields of science humanitieshistory and archaeologyhistorynatural sciencescomputer and information sciencesartificial intelligencemachine learningreinforcement learningnatural sciencescomputer and information sciencesartificial intelligencemachine learningdeep learningengineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringroboticsnatural sciencescomputer and information sciencesartificial intelligencecomputational intelligence Keywords INFLUENCE Programme(s) H2020-EU.1.1. - EXCELLENT SCIENCE - European Research Council (ERC) Main Programme Topic(s) ERC-2017-STG - ERC Starting Grant Call for proposal ERC-2017-STG See other projects for this call Funding Scheme ERC-STG - Starting Grant Host institution TECHNISCHE UNIVERSITEIT DELFT Net EU contribution € 1 475 560,00 Address STEVINWEG 1 2628 CN Delft Netherlands See on map Region West-Nederland Zuid-Holland Delft en Westland Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Total cost € 1 475 560,00 Beneficiaries (2) Sort alphabetically Sort by Net EU contribution Expand all Collapse all TECHNISCHE UNIVERSITEIT DELFT Netherlands Net EU contribution € 1 475 560,00 Address STEVINWEG 1 2628 CN Delft See on map Region West-Nederland Zuid-Holland Delft en Westland Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Total cost € 1 475 560,00 THE UNIVERSITY OF LIVERPOOL Participation ended United Kingdom Net EU contribution € 0,00 Address BROWNLOW HILL 765 FOUNDATION BUILDING L69 7ZX Liverpool See on map Region North West (England) Merseyside Liverpool Activity type Higher or Secondary Education Establishments Links Contact the organisation Opens in new window Website Opens in new window Participation in EU R&I programmes Opens in new window HORIZON collaboration network Opens in new window Total cost No data