Project description DEENESFRITPL Optimising decision-theoretic planning for autonomous agents Autonomous agents can sense and act in their environment to perform designated tasks without human intervention. In the foreseeable future, they could prove invaluable in homes, factories, e-commerce, high-risk environments and more. Therefore, designing agents that perform reliably in diverse settings is a priority for AI. However, the main challenge is to overcome barriers in formulating an agent’s policy, such as costly policy evaluation that requires multiple trials. Funded by the European research Council, the CoPS project aims to develop a new class of decision-theoretic planning methods that simultaneously optimise policies and the way in which they are evaluated. This approach automatically identifies the best scenarios, thus reducing the need for random sampling. Show the project objective Hide the project objective Objective I propose to develop a new class of decision-theoretic planning methods that overcome fundamental obstacles to the efficient optimization of autonomous agents. Creating agents that are effective in diverse settings is a key goal of artificial intelligence with enormous potential implications: robotic agents would be invaluable in homes, factories, and high-risk settings; software agents could revolutionize e-commerce, information retrieval, and traffic control.The main challenge lies in specifying an agent's policy: the behavioral strategy that determines its actions. Since the complexity of realistic tasks makes manual policy construction hopeless, there is great demand for decision-theoretic planning methods that automatically discover good policies. Despite enormous progress, the grand challenge of efficiently discovering effective policies for complex tasks remains unmet.A fundamental obstacle is the cost of policy evaluation: estimating a policy's quality by averaging performance over multiple trials. This cost grows quickly with increases in task complexity (making trials more expensive) or stochasticity (necessitating more trials). To address this difficulty, I propose a new approach that simultaneously optimizes both policies and the manner in which those policies are evaluated. The key insight is that, in many tasks, many trials are wasted because they do not elicit the controllable rare events critical for distinguishing between policies. Thus, I will develop methods that leverage coevolution to automatically discover the best events, instead of sampling them randomly.If successful, this project will greatly improve the efficiency of decision-theoretic planning and, in turn, help realize the potential of autonomous agents. In addition, by automatically identifying the most useful events, the resulting methods will help isolate critical factors in performance and thus yield new insights into what makes decision-theoretic problems hard. Fields of science natural sciencescomputer and information sciencessoftwarenatural sciencesmathematicsapplied mathematicsstatistics and probabilitybayesian statisticsnatural sciencesmathematicspure mathematicsmathematical analysisfourier analysisnatural sciencescomputer and information sciencesartificial intelligencemachine learningreinforcement learningnatural sciencesbiological sciencesevolutionary biology Programme(s) H2020-EU.1.1. - EXCELLENT SCIENCE - European Research Council (ERC) Main Programme Topic(s) ERC-StG-2014 - ERC Starting Grant Call for proposal ERC-2014-STG See other projects for this call Funding Scheme ERC-STG - Starting Grant Host institution THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD Net EU contribution € 1 480 632,00 Address WELLINGTON SQUARE UNIVERSITY OFFICES OX1 2JD Oxford United Kingdom See on map Region South East (England) Berkshire, Buckinghamshire and Oxfordshire Oxfordshire 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 € 1 480 632,00 Beneficiaries (1) Sort alphabetically Sort by Net EU contribution Expand all Collapse all THE CHANCELLOR, MASTERS AND SCHOLARS OF THE UNIVERSITY OF OXFORD United Kingdom Net EU contribution € 1 480 632,00 Address WELLINGTON SQUARE UNIVERSITY OFFICES OX1 2JD Oxford See on map Region South East (England) Berkshire, Buckinghamshire and Oxfordshire Oxfordshire 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 € 1 480 632,00
