PhD Position Reinforcement Learning Theory

3 weken geleden


Delft, Nederland TU Delft Voltijd
Job description

We are looking for a motivated candidate to work on the topics of theoretical machine learning, specifically in the domain of sequential decision-making, which includes bandit problems and theoretical reinforcement learning. The primary objective of this project is to analyze and design learning algorithms and provide formal guarantees regarding their performance. To achieve this, you will use your skills in advanced mathematical and statistical techniques. The project is situated in the context of efficient online learning, with a focus on scaling with model complexity and function approximation.

You will be welcomed into our Sequential Decision-Making group, where we focus on various aspects of reinforcement learning. During your PhD, you will have the opportunity to tackle challenging problems related to developing advanced function approximation methods and robust reinforcement learning techniques. You will delve deeply into the rapidly evolving field of reinforcement learning theory, while also exploring relevant areas of mathematics.

Requirements

  • Hold a master's degree in mathematics, computer science, physics, or a related discipline.
  • Demonstrate eagerness to tackle complex mathematical challenges.
  • Have proficiency in both written and spoken English.
  • Good mathematical background, including knowledge of statistics and optimization. Background in machine learning is a plus..

Doing a PhD at TU Delft requires English proficiency at a certain level to ensure that the candidate is able to communicate and interact well, participate in English-taught Doctoral Education courses, and write scientific articles and a final thesis. For more details please check the .

Conditions of employment

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1,5 year contract with an official go/no go progress assessment within 15 months. Followed by an additional contract for the remaining 2,5 years assuming everything goes well and performance requirements are met.

Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2770 per month in the first year to € 3539 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.

T he TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution . Flexible work schedules can be arranged.

For international applicants, TU Delft has the . This service provides information for new international employees to help you prepare the relocation and to settle in the Netherlands. The Coming to Delft Service offers a for partners and they organise events to expand your (social) network.

TU Delft (Delft University of Technology)

Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.

At TU Delft we embrace diversity as one of our core and we actively to be a university where you feel at home and can flourish. We value different perspectives and qualities. We believe this makes our work more innovative, the TU Delft community more vibrant and the world more just. Together, we imagine, invent and create solutions using technology to have a positive impact on a global scale. That is why we invite you to apply. Your application will receive fair consideration.

Challenge. Change. Impact

Faculty Electrical Engineering, Mathematics and Computer Science

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) brings together three scientific disciplines. Combined, they reinforce each other and are the driving force behind the technology we all use in our daily lives. Technology such as the electricity grid, which our faculty is helping to make completely sustainable and future-proof. At the same time, we are developing the chips and sensors of the future, whilst also setting the foundations for the software technologies to run on this new generation of equipment – which of course includes AI. Meanwhile we are pushing the limits of applied mathematics, for example mapping out disease processes using single cell data, and using mathematics to simulate gigantic ash plumes after a volcanic eruption. In other words: there is plenty of room at the faculty for ground-breaking research. We educate innovative engineers and have excellent labs and facilities that underline our strong international position. In total, more than 1000 employees and 4,000 students work and study in this innovative environment.

Click  to go to the website of the Faculty of Electrical Engineering, Mathematics and Computer Science.



  • Delft, Zuid-Holland, Nederland TU Delft Voltijd

    Job description We are looking for a motivated candidate to work on the topics of theoretical machine learning, specifically in the domain of sequential decision-making, which includes bandit problems and theoretical reinforcement learning. The primary objective of this project is to analyze and design learning algorithms and provide formal guarantees...


  • Delft, Nederland Delft University of Technology Voltijd

    Teaser Challenge: Enhancing the modelling of uncertainties in policing. Change: Harnessing AI to identify and prioritise uncertainties, and predict responses. Impact: Driving police effectiveness in interventions. Job description When fighting crime, it is crucial to be able to forecast how actors are going to respond to actions. Whether the police acts on...


  • Delft, Zuid-Holland, Nederland Delft University of Technology Voltijd

    TeaserChallenge: Enhancing the modelling of uncertainties in policing.Change: Harnessing AI to identify and prioritise uncertainties, and predict responses.Impact: Driving police effectiveness in interventions.Job descriptionWhen fighting crime, it is crucial to be able to forecast how actors are going to respond to actions. Whether the police acts on...


  • Delft, Zuid-Holland, Nederland Delft University of Technology Voltijd

    TeaserChallenge: Enhancing the modelling of uncertainties in policing.Change: Harnessing AI to identify and prioritise uncertainties, and predict responses.Impact: Driving police effectiveness in interventions.Job descriptionWhen fighting crime, it is crucial to be able to forecast how actors are going to respond to actions. Whether the police acts on...


  • Delft, Nederland Delft University of Technology Voltijd

    Teaser Challenge: Developing non-Markovian theory on time-varying networks to enhance or prevent the spread in networks. Change: Adopting the theory of non-Markovian processes on networks. Impact: Robust networks to reduce the impact of network failures or epidemics; prevent viral epidemics in human population. Job description Epidemic processes widely apply...


  • Delft, Zuid-Holland, Nederland Technische Universiteit Delft (TU Delft) Voltijd

    PhD Decentralised Machine Learning 36-40 hours per week Challenge : Developing and building a fully decentralised video search engine.Change : Eliminating the need for servers when developing machine learning.Impact : Safe machine learning benefiting billions of users.Job Position With the growing number of mobile devices, there is an incredible increase in...


  • Delft, Nederland TU Delft Voltijd

    Job description TU Delft is a top-tier university and we have been growing in our investment in the field of Artificial intelligence. Within the University, the Management in the Built Environment (MBE) Department strives for a sustainable built environment in which the interests of the end user and other stakeholders are the starting point. MBE...


  • Delft, Nederland TU Delft Voltijd

    Job description TU Delft is a top-tier university and we have been growing in our investment in the field of Artificial intelligence. Within the University, the Management in the Built Environment (MBE) Department strives for a sustainable built environment in which the interests of the end user and other stakeholders are the starting point. MBE...


  • Delft, Nederland TU Delft Voltijd

    Job description When fighting crime, it is crucial to be able to forecast how actors are going to respond to actions. Whether the police acts on information captured, or intervenes in e.g. a money laundering or drugs chain, any action will provoke an uncertain reaction. As a PhD candidate at TU Delft, you will bridge fundamental research and...


  • Delft, Nederland TU Delft Voltijd

    PhD Position Multivariate Dependence Modelling and Statistical Machine Learning Algorithms for Patient Risk Profiling- Do you love exploring new ideas and want to positively impact healthcare by developing new mathematical methods? We're seeking a motivated person to join us as a PhD researcher in our group. Job description The project will be...


  • Delft, Nederland TU Delft Voltijd

    Job description Epidemic processes widely apply to biological and computer network viruses, to cascading failures in power grids, to the spread of news, rumour or emotions in a social network, to transactions in banking networks and to the processing of functions and movements in the human brain. An epidemic process spreads over an underlying...


  • Delft, Nederland TU Delft Voltijd

    Job description Epidemic processes widely apply to biological and computer network viruses, to cascading failures in power grids, to the spread of news, rumour or emotions in a social network, to transactions in banking networks and to the processing of functions and movements in the human brain. An epidemic process spreads over an underlying...


  • Delft, Zuid-Holland, Nederland Delft University of Technology Voltijd

    Job descriptionDrones have become increasingly prevalent in various domains including agriculture, environmental monitoring, search and rescue, and surveillance. To realise their full potential, new methods are needed to support autonomous decision-making within unstructured, dynamic environments.Conventional approaches to drone mission planning often rely...


  • Delft, Zuid-Holland, Nederland Delft University of Technology Voltijd

    Job descriptionDrones have become increasingly prevalent in various domains including agriculture, environmental monitoring, search and rescue, and surveillance. To realise their full potential, new methods are needed to support autonomous decision-making within unstructured, dynamic environments.Conventional approaches to drone mission planning often rely...


  • Delft, Zuid-Holland, Nederland Delft University of Technology Voltijd

    We are seeking for a highly-skilled and self-motivated candidate with a strong mathematical background to do a Ph.D. on the fundamental aspects of graph machine learning with applications to renewables.Job descriptionGraphs are playing an ever increasing role in nowadays systems as a flexible tool to model complex systems. In addition, these systems generate...


  • Delft, Zuid-Holland, Nederland Delft University of Technology Voltijd

    We are seeking for a highly-skilled and self-motivated candidate with a strong mathematical background to do a Ph.D. on the fundamental aspects of graph machine learning with applications to renewables.Job descriptionGraphs are playing an ever increasing role in nowadays systems as a flexible tool to model complex systems. In addition, these systems generate...


  • Delft, Zuid-Holland, Nederland TU Delft Voltijd

    Job description We are looking for a motivated candidate to work on the topics of theoretical machine learning, specifically in the domain of sequential decision making, which includes bandit problems and theoretical reinforcement learning. The primary objective of this project is to analyze and design learning algorithms and provide formal guarantees...


  • Delft, Zuid-Holland, Nederland TU Delft Voltijd

    Job DescriptionEpidemic processes are widely observed in various areas ranging from biological and computer network viruses to the spread of news and emotions in social networks. As a PhD student at TU Delft, you will conduct research focusing on non-Markovian models in Network Science to predict and prevent spread in networks.Your research may include data...


  • Delft, Nederland TU Delft Voltijd

    Job description Drones have become increasingly prevalent in various domains including agriculture, environmental monitoring, search and rescue, and surveillance. To realise their full potential, new methods are needed to support autonomous decision-making within unstructured, dynamic environments. Conventional approaches to drone mission...


  • Delft, Nederland TU Delft Voltijd

    Job description Drones have become increasingly prevalent in various domains including agriculture, environmental monitoring, search and rescue, and surveillance. To realise their full potential, new methods are needed to support autonomous decision-making within unstructured, dynamic environments. Conventional approaches to drone mission...