PhD-TA on safe reinforcement learning in partially observable settings

PhD-TA on safe reinforcement learning in partially observable settings

Published Deadline Location
25 Nov 22 Dec Eindhoven

You cannot apply for this job anymore (deadline was 22 Dec 2024).

Browse the current job offers or choose an item in the top navigation above.

Are you eager to work on AI safety, unleashing the potential of reinforcement learning for production environments?

Job description

Position

We are looking for an enthusiastic PhD-TA candidate to work on advancing the field of sequential decision making under partial observations, with a particular focus on safe reinforcement learning methodologies. The primary objective is to build AI agents that, given a limited number of sensors, can operate safely in an unknown environment. The project focuses on the development of novel methods that can learn models of the world dedicated to safety. Such a model may be built based on the experiences of the agent or historical data collected by a different agent.

Program

During your PhD, you will have the opportunity to tackle challenging problems related to the use of memory, feature extraction, and representation learning.  You will delve deeply into the rapidly evolving field of reinforcement learning, while also exploring relevant areas of machine learning.

Group

You will work on the Data and AI cluster, where you will have the chance to collaborate with experts designing new AI methods, algorithms and tools to expand the reach of AI and its generalization abilities, focusing particularly on the foundational issues of robustness and safety. The cluster offers a inclusive and collaborative workspace with numerous opportunities for social interactions.

Application and Supervision

The position is available from December 1st and will be performed under the supervision of Dr. Thiago D. Simão (httpss://tdsimao.github.io).

Specifications

Eindhoven University of Technology (TU/e)

Requirements

  • A master's degree (or an equivalent university degree) in Computer Science, Mathematics, Physics, or related discipline.
  • Experience with decision-making frameworks (MDP, POMDP, bandits, dynamical systems, etc).
  • Experience in programming and empirical analysis in machine learning (Python, PyTorch, etc).
  • Excellent problem-solving skills and ability to work independently and collaboratively.
  • Strong written and oral communication skills in English.
  • Motivated to develop your teaching skills and coach students.

Conditions of employment

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:
  • Full-time employment for five years, with an intermediate evaluation (go/no-go) after nine months. You will spend 25% of your employment on teaching tasks.
  • Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale P (min. €2,901 max. €3,707).
  • A year-end bonus of 8.3% and annual vacation pay of 8%.
  • High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process.
  • An excellent technical infrastructure, on-campus children's day care and sports facilities.
  • An allowance for commuting, working from home and internet costs.
  • Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates. 

Specifications

  • PhD
  • Engineering
  • max. 38 hours per week
  • University graduate
  • V32.7890

Employer

Eindhoven University of Technology (TU/e)

Learn more about this employer

Location

De Rondom 70, 5612 AP, Eindhoven

View on Google Maps

Interesting for you