PhD Candidate in Complex Reinforcement Learning and Geometrical Aperiodic Environments at the Donders Centre for Cognition
PhD Candidate in Complex Reinforcement Learning and Geometrical Aperiodic Environments at the Donders Centre for Cognition
Job description
Do you have a strong background in scientific programming and experience with open-source code practices? And do you want to collaborate and interact with renowned international experts in machine learning, computational neuroscience and neuromorphic computing? Then join us at the Donders Institute. As a PhD Candidate, you will be responsible for innovating and creating state-of-the-art algorithms in complex systems.
We invite applications for a PhD position on reinforcement learning for aperiodic structures, with emphasis on single and multi-agent learning. This project is embedded in the Donders institute and the AI department of Radboud University. The aim is to develop robust reinforcement learning algorithms and gym environments to tackle navigation in aperiodic structures, with emphasis on task achievement and agent communication. This work entails a theoretical (mathematical) understanding of random systems, dynamic information theory and deep reinforcement learning, alongside testing and/or implementation of these algorithms in the form of novel gym environments for agent-based artificial neural network modelling. As a PhD candidate, you will be responsible for development and validation of the math and models under supervision of expert staff in machine learning.
We offer you a full time (100%) position for 4 years. This project is supervised by Dr Tal Kachman and Prof. van Gerven (PhD supervisor). You will be employed at the Artificial Intelligence department of the Donders Institute for Brain, Cognition and Behaviour and have the opportunity to collaborate and interact with renowned international experts in machine learning, computational neuroscience and neuromorphic computing. You will also benefit from the extensive training programme offered by the Donders Graduate School. Additionally, you will have the opportunity to supervise MSc and BSc students in their (honours) thesis projects.
You will be responsible for innovating and creating state-of-the-art algorithms in complex systems such as reinforcement learning environments with emphasis on multi-agent interactions. This will also entail creating production level research code in Python, C++, and generating open-source knowledge base. Knowledge dissemination is an integral part, and you will be expected to publish extensively as well as give invited seminars talks and produce general-purpose
content such as blogs.
This position does not include a teaching assignment.
We invite applications for a PhD position on reinforcement learning for aperiodic structures, with emphasis on single and multi-agent learning. This project is embedded in the Donders institute and the AI department of Radboud University. The aim is to develop robust reinforcement learning algorithms and gym environments to tackle navigation in aperiodic structures, with emphasis on task achievement and agent communication. This work entails a theoretical (mathematical) understanding of random systems, dynamic information theory and deep reinforcement learning, alongside testing and/or implementation of these algorithms in the form of novel gym environments for agent-based artificial neural network modelling. As a PhD candidate, you will be responsible for development and validation of the math and models under supervision of expert staff in machine learning.
We offer you a full time (100%) position for 4 years. This project is supervised by Dr Tal Kachman and Prof. van Gerven (PhD supervisor). You will be employed at the Artificial Intelligence department of the Donders Institute for Brain, Cognition and Behaviour and have the opportunity to collaborate and interact with renowned international experts in machine learning, computational neuroscience and neuromorphic computing. You will also benefit from the extensive training programme offered by the Donders Graduate School. Additionally, you will have the opportunity to supervise MSc and BSc students in their (honours) thesis projects.
You will be responsible for innovating and creating state-of-the-art algorithms in complex systems such as reinforcement learning environments with emphasis on multi-agent interactions. This will also entail creating production level research code in Python, C++, and generating open-source knowledge base. Knowledge dissemination is an integral part, and you will be expected to publish extensively as well as give invited seminars talks and produce general-purpose
content such as blogs.
This position does not include a teaching assignment.
Specifications
- €2541—€3247 per month
- Nijmegen View on Google Maps
:fill(white)/logos/run-en-wide.jpg)
Radboud University
Requirements
- You should have exceptional mathematical skills and a deep understanding of reinforcement learning with emphasis on complex interactions, dynamical systems, deep learning, machine learning and algorithmic foundations.
- You will be expected to have a strong background in scientific programming, experience with open-source code practices with a proven code base, and a track record of publications in the aforementioned fields.
- You should also have experience with mentoring and guiding students and collaborative work.
- Ideally, you will also have a proven track record of performing research in international environments.
Conditions of employment
Fixed-term contract: You will be employed for an initial period of 18 months, after which your performance will be evaluated. If the evaluation is positive, the contract will be extended by 2.5 years (4 year contract).
- It concerns an employment for 1.0 FTE.
- The gross starting salary amounts to €2,541 per month based on a 38-hour working week, and will increase to €3,247 in the fourth year (salary scale P).
- You will receive 8% holiday allowance and 8.3% end-of-year bonus.
- You will be employed for an initial period of 18 months, after which your performance will be evaluated. If the evaluation is positive, the contract will be extended by 2.5 years (4 year contract).
- You will be able to use our Dual Career and Family Care Services. Our Dual Career and Family Care Officer can assist you with family-related support, help your partner or spouse prepare for the local labour market, provide customized support in their search for employment and help your family settle in Nijmegen.
- Working for us means getting extra days off. In case of full-time employment, you can choose between 30 or 41 days of annual leave instead of the legally allotted 20.
- You will be part of the Donders Graduate School for Cognitive Neuroscience
Employer
The Donders Institute for Brain, Cognition and Behaviour is a world-class interfaculty research centre, that houses more than 700 researchers devoted to understanding the mechanistic underpinnings of the human mind. Research at the Donders Institute is focused around four themes: 1. Language and communication, 2. Perception, action and control, 3. Plasticity and memory, 4. Neural computation and neurotechnology. Excellent, state-of-the-art research facilities are available for the broad range of neuroscience research that is being conducted at the Donders Institute. The Donders Institute has been assessed by an international evaluation committee as ‘excellent’ and recognised as a ‘very stimulating environment for top researchers, as well as for young talent’. The Donders Institute fosters a collaborative, multidisciplinary, supportive research environment with a diverse international staff. English is the lingua franca at the Institute.
Radboud University
We want to get the best out of science, others and ourselves. Why? Because this is what the world around us desperately needs. Leading research and education make an indispensable contribution to a healthy, free world with equal opportunities for all. This is what unites the more than 24,000 students and 5,600 employees at Radboud University. And this requires even more talent, collaboration and lifelong learning. You have a part to play!
Additional information
For questions about the position, please contact Tal Kachman, Assistant Professor at tal.kachman@donders.ru.nl.
Specifications
- PhD; Research, development, innovation
- Behaviour and society
- €2541—€3247 per month
- University graduate
- 1210690
Employer
Location
Interesting for you
Apply for this job
Apply for this job
This application process is managed by the employer (Radboud University). Please contact the employer for questions regarding your application.
Thank you for applying
Please contact the employer for questions regarding your application.
Tip: save this job as favorite in your AcademicTransfer account. This gives you an immediate overview and makes it easy to find the job later on. No account yet? Create it now and take advantage of other useful functionalities too!
Application procedure
You can apply until 23 June 2023, exclusively using the button below. Kindly address your application to Tal Kachman. Please fill in the application form and attach the following documents:- A motivation letter
- Your CV, including two recommendation letters
- A peer-reviewed preprint
- An open-source code reference
We can imagine you're curious about our application procedure. It offers a rough outline of what you can expect during the application process, how we handle your personal data and how we deal with internal and external candidates.
Application procedure
Application procedure
You can apply until 23 June 2023, exclusively using the button below. Kindly address your application to Tal Kachman. Please fill in the application form and attach the following documents:- A motivation letter
- Your CV, including two recommendation letters
- A peer-reviewed preprint
- An open-source code reference
We can imagine you're curious about our application procedure. It offers a rough outline of what you can expect during the application process, how we handle your personal data and how we deal with internal and external candidates.
Make sure to apply no later than 23 Jun 2023 23:59 (Europe/Amsterdam).