Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Employer
- NEW YORK UNIVERSITY ABU DHABI
- Delft University of Technology (TU Delft)
- Technical University of Munich
- CNRS
- Télécom Paris
- Aalborg University
- Bar Ilan University
- Eindhoven University of Technology (TU/e)
- Empa
- IMT Mines Albi
- KTH Royal Institute of Technology
- Lodz University of Technology
- MOHAMMED VI POLYTECHNIC UNIVERSITY
- Tampere University
- The University of Arizona
- Tilburg University
- University of Amsterdam (UvA)
- University of Cambridge;
- University of Minnesota
- Université catholique de Louvain
- XIAN JIAOTONG LIVERPOOL UNIVERSITY (XJTLU)
- 11 more »
- « less
-
Field
-
. Please do not contact us for unsolicited services. Where to apply Website https://www.academictransfer.com/en/jobs/357285/postdoc-reinforcement-learning-… Requirements Additional Information Website
-
cutting-edge analytical approaches (Multilevel Vector Autoregressive Models, Dynamic Structural Equation Modelling, Hidden Markov Models, Causal discovery algorithms, Reinforcement Learning), Contributing
-
of interest include: Robot modelling, Nonlinear and Optimal control, Reinforcement learning, and Data-driven modeling and control. The Post-Doctoral associate will be based at NYU Abu Dhabi and will directly
-
scienceEducation LevelPhD or equivalent Skills/Qualifications PhD in computer science Background in probability, Markov chains, MDPs Knowledge about reinforcement learning and planning are a plus but not necessary
-
, decision-making and control using data, have been proposed. For control or management applications, reinforcement learning (RL/DRL), a branch of machine learning, is a promising solution that involves
-
mandatory fields (*) and kindly use “Provably Safe Reinforcement Learning” as the “Title of Position”. Please do not include a cover letter. Further similar job offerings will be announced on https
-
and economy that respect people and their environment. We are looking for our future postdoctoral researcher in model-based reinforcement learning to join the Computer Science and Networks (INFRES
-
such as pre-ignition risks, material compatibility, and storage under high pressure. To address these challenges, we will develop novel techniques for provably safe reinforcement learning. This project is
-
, including reinforcement learning and multiobjective stochastic optimisation. These methods will be applied to cooling solutions at the building, district, and city scale, where innovative and energy-efficient
-
language models and reinforcement learning for real-time optimization, fault self-recovery, and production scheduling in industrial processes. Publish research results in top-tier international conferences