www.acad.jobs : academic jobs worldwide – and the best jobs in industry
                
     
Position: PhD in Collaborative multi-agent deep reinforcement learning: enabling communication and relational learning
Institution: University of Warwick
Location: Warwick, United Kingdom
Duties: In this PhD project, you will develop a general graph-based framework to (a) facilitate efficient multi-agent communication, (b) enable learning using sparse rewards (i.e. feedback signals that are non-zero only when a goal is achieved), and (c) build a relational representation of the environment. You will be joining a larger research team based at WMG (Warwick Manufacturing Group) at the University of Warwick working on various deep reinforcement learning problems and will support the development of an open-source library of multi-agent tasks with strong connections to industry
Requirements: Candidates should have an MSc in Statistics, Computer Science, Engineering or similar quantitative background and very strong and demonstrable programming skills especially in Python
   
Text: Skip to main content Skip to navigation Sign in Study Research Business Alumni News Engagement Search Warwick Search Shaping the future About WMG Our Journey Our presence on campus WMG Success Stories Public engagement and Outreach Contact us Business How we work with business Support for SMEs Accelerator Education Undergraduate (full-time) Undergraduate (part-time) Degree Apprenticeships For employers Postgraduate (full-time) Postgraduate (part-time) Custom Programmes Research Degrees Overseas Programmes WMG Alumni Research Digital Technologies Organisational and Societal Transformation Intelligent Vehicles Materials and Manufacturing Energy Careers Working at WMG How to apply Graduate Development Programme Visiting Research Fellows, Chairs and Professors News and Events News Experts directory WMG events Social media Media contacts Our People WMG Insights WMG Talks Athena SWAN Education Research Degrees Vacancies PhD Collaborative multi-agent deep reinforcement learning: enabling communication and relational learning PhD Collaborative multi-agent deep reinforcement learning: enabling communication and relational learning PhD in Collaborative multi-agent deep reinforcement learning: enabling communication and relational learning Project Overview One of the main challenges in AI today is that of autonomous sequential decision-making: how can we give algorithms the ability to decide what actions to take whilst interacting with an uncertain environment in order to achieve a goal? Remarkable developments in this direction over the last few years have relied on deep reinforcement learning (DRL), which is based on the mathematical formalism of Markov decision processes (MDPs), using artificial neural networks as flexible function approximators. Many real-world applications are characterised by the interplay of multiple decision-makers that operate in the same shared-resources environment and need to accomplish goals cooperatively. Some of the most advanced industrial multi-agent systems in the world today are assembly lines and warehouse management systems. Whether the agents are robots, autonomous vehicles or clinical decision-makers, there is a strong desire for and increasing commercial interest in these systems: they are attractive because they can operate on their own in the world, alongside humans, under realistic constraints. Multi-agent reinforcement learning has been studied since the 1990s; however, the last five years have been characterised by a remarkable boost in academic and commercial activity, fuelled by ground-breaking advances in deep neural networks along with the increasing power and decreasing cost of computing. The fast-developing area of multi-agent deep reinforcement learning (MADRL) has emerged to extend DRL to teams of autonomous agents. However, apart from a handful of highly specialised systems, the number of real-world applications powered by MADRL has still been limited. As part of this PhD project, which is part of a UKRI Turing AI Acceleration Fellowship, you contribute to the emerging area of MADRL with a view to unleashing its full potential. You will consider the cooperative MADRL problem, in which a system of several learning agents must jointly optimise a single reward signal - the team reward - accumulated over time. Each agent has local autonomy: it can access its local observations and choose actions from its own action space. One of the most significant challenges in this context is how to foster collaborative behaviour within the system. The fundamental enabler of cooperative multi-agent skills is the ability to develop adequate communication. In previous work, we have demonstrated how explicit communication patterns emerge in systems equipped with a differential memory learned end-to-end through policy gradient methods. Even when every agent has access to every other agent’s observations, communication mechanisms still need to be learned for the task at hand to improve coordination because the information that agents possess at a given time may be noisy or not necessarily relevant regarding informing other agents’ decisions. In this PhD project, you will develop a general graph-based framework to (a) facilitate efficient multi-agent communication, (b) enable learning using sparse rewards (i.e. feedback signals that are non-zero only when a goal is achieved), and (c) build a relational representation of the environment. You will be joining a larger research team based at WMG (Warwick Manufacturing Group) at the University of Warwick working on various deep reinforcement learning problems and will support the development of an open-source library of multi-agent tasks with strong connections to industry. Candidates should have an MSc in Statistics, Computer Science, Engineering or similar quantitative background and very strong and demonstrable programming skills especially in Python. For informal enquires please contact Professor Giovanni Montana: g.montana@warwick.ac.uk. Funding and Eligibility Standard PhD at UKRI rates: £15,285 - 3.5 Years Available to eligible Home fee status and UK domicile EU students Essential and desirable criteria Prospective candidates are expected to have a minimum 2.1 undergraduate (BEng, MEng, BSc, MSci) and/or postgraduate masters’ qualification (MSc) with 65% or above. Candidates should have an MSc in Statistics, Computer Science, Engineering or similar quantitative background and very strong and demonstrable programming skills especially in Python. To apply To apply please complete our online enquiry form and upload your CV. Please ensure you meet the minimum requirements before filling in the online form. Key Information: Funding source: EPSRC DTP Stipend: Standard PhD at UKRI rates: £15,285 Supervisor: Prof Giovanni Montana Available to eligible Home fee status and UK domicile EU students Start date: October 2021 Education programmes Undergraduate (full-time) Undergraduate (part-time) Degree Apprenticeships Postgraduate (full-time) Postgraduate (part-time) Custom programmes Research Degrees Overseas Programmes Research themes Digitally Enhanced Manufacturing Health and Wellbeing Intelligent Vehicles Materials and Manufacturing Transport Electrification Business support News Events Contact us WMG, International Manufacturing Centre, University of Warwick, Coventry, CV4 7AL, United Kingdom Business Education Research News and Events Contact us Staff Intranet Current students Twitter Facebook YouTube iTunes U LinkedIn Page contact: Ella Southall Last revised: Fri 23 Jul 2021 Powered by Sitebuilder © MMXXI Terms Privacy Cookies Accessibility Coronavirus (Covid-19): Latest updates and information Let us know you agree to cookies We use cookies to give you the best online experience. Please let us know if you agree to functional, advertising and performance cookies. You can update your cookie preferences at any time. Cookie policy Essential cookies Functional cookies Advertising cookies Performance cookies Accept all Remember my preference More information
Please click here, if the job didn't load correctly.
Your browser does not support iframes. Please click <a href="https://www.acad.jobs/job.php?t_id=J000350245&redirect" target="_parent" style="color:#7A7A7A">here</a>, if the job didn't load correctly.