or a postdoctoral research position (two years, 40hours/week), starting as soon as possible. The successful applicant will carry out his/her postdoc/PhD
in the research area of formal methods applied to guide autonomous agents based on reinforcement learning. The position is in the context of the
research project TAIGER: Training and Guiding AI Agents with Ethical Rules, aiming at designing autonomous agents sensitive to (ethical, legal and social) norms.
The specific requirements for the PostDoc position are the following:
· A completed PhD in Computer Science or related fields
· Experience in developing tools
· Solid experience in reinforcement learning method and formal methods
· Knowledge of logic
· Very good English skills (writing, speaking)
· A promising publication record
The specific requirements for the PhD position are the following:
· A completed Master in Computer Science or related fields
· Solid experience in reinforcement learning methods and preferably formal methods
· Knowledge of logic
· Very good English skills (writing, speaking)
About TU Wien (https://www.tuwien.at/en/tu-wien/about-tu-wien)
The TU Wien is Austria's largest research and educational institution in the field of technology and natural sciences. More than 4,000 scientists are researching
"technology for people" in five main research areas at eight faculties. The content of the studies offered is derived from the excellent research. More than
26,000 students in 62 degree programmes benefit from this. As a driver of innovation, TU Wien strengthens the business location, facilitates cooperation and
contributes to the prosperity of society.
Doctoral Program in Trustworthy Autonomous Cyber-Physical Systems
The PhD student will be affiliated with the new PhD program in Trustworthy Autonomous Cyber-Physical Systems.
TAIGER Project (https://taiger.logic.at/abstract)
Autonomous agents are increasingly becoming an integral part of our world. It is essential that they act in legal, ethically-sensitive, and socially acceptable ways;
more broadly, their behavior must be regulated by norms. While the crucial importance of this endeavor is well-acknowledged, the question of how to implement
such agents is still open.
Two different approaches emerge: one approach uses symbolic Artificial Intelligence (AI) techniques (Logic, Knowledge Representation and Reasoning),
while the other relies on sub-symbolic AI (i.e., Machine Learning), where in particular Reinforcement Learning (RL) has proven to be a powerful technique to train
autonomous agents to solve complex tasks in sophisticated environments.
As both approaches have strengths and weaknesses, the three partners of TAIGER: E. Bartocci (Cyber-Physical Systems), A. Ciabattoni (Logic), and T. Eiter
(Knowledge Representation and Answer Set Programming), aim to integrate them, thus getting the best of both worlds.
Specifically, TAIGER will introduce effective frameworks for equipping RL-based agents with the ability to comply with norms in possible interplay with their goals.
Grounded in formal reasoning, the frameworks will be modular and facilitate transparent justification of judgments. Moreover, they will cope with potential contradictions
in normative requirements and handle situations in which no compliance is possible, without deviating too much from the optimal behavior the agent has learned.
Salary
The salary of the postdoctoral researcher will be of around 4,351.90 Euro (gross) x 14 times = 60,926.6 Euro (gross). The salary of the doctoral researcher will be
around 2,464.80 Euro x 14 times = 34,507.2 Euro (gross).
Applications, including any attachments, should be submitted by the 20th of January 2024 to the following email addresses: ezio.bartocci@tuwien.ac.at, agata@logic.at
The following documents must be attached to the application:
· Cover letter stating the candidate's motivation to apply, and the reason(s) why they should be selected for the position
· CV
· sample of a project of the applicant (e.g., Master thesis for PhD students)
· two reference letters
Contact details
For further information and enquiries about this post please contact Prof. Ezio Bartocci, e-mail: ezio.bartocci@tuwien.ac.at.
**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************
Posts
