Sort by
Refine Your Search
-
Listed
-
Category
-
Country
-
Employer
- Delft University of Technology (TU Delft)
- University of Antwerp
- Aalborg University
- Eindhoven University of Technology (TU/e)
- NTNU - Norwegian University of Science and Technology
- University of Copenhagen
- XIAN JIAOTONG LIVERPOOL UNIVERSITY (XJTLU)
- ;
- CNRS
- Copenhagen Business School
- Delft University of Technology
- Durham University
- Erasmus University Rotterdam
- Harvard University
- ICN2
- Leiden University
- Luxembourg Institute of Science and Technology (LIST)
- TU Delft
- Technical University of Denmark
- The University of Manchester
- UNIVERSITAT POMPEU FABRA
- Universidade de Coimbra
- University of Amsterdam (UvA)
- University of Bergen
- University of Bristol
- University of Cambridge;
- University of Luxembourg
- University of Sheffield;
- University of Southern Queensland
- University of Texas at El Paso
- University of Warwick
- Utrecht University
- 22 more »
- « less
-
Field
-
actively on the preparation and defence of a PhD thesis in the field of explainable reinforcement learning (XRL). Explainable reinforcement learning aims to make decisions, policies, and learning processes
-
actively on the preparation and defence of a PhD thesis in the field of continual reinforcement learning. Continual reinforcement learning studies how agents can learn across a sequence of changing tasks
-
thesis in the field of continual reinforcement learning. Continual reinforcement learning studies how agents can learn across a sequence of changing tasks, environments, or objectives while retaining
-
Details Title Postdoctoral Fellow in Computer Science — From Theory to Practice: Reinforcement Learning for Large Scale Foundation Model Post‑Training School Harvard John A. Paulson School of
-
reinforcement learning (RL), active learning, Bayesian decision theory, and stochastic optimisation for partially observed and evolving systems. Key research directions include: adaptive data acquisition
-
and large models, limiting real-world deployment. This PhD focuses on efficient Physical AI, emphasising data-efficient training, reinforcement learning, continual adaptation and edge deployment
-
and behavioural experimentation. Key research tasks include: Developing learning-based behavioural models of navigation, route choice and adaptation; Applying reinforcement learning, probabilistic
-
reinforcement learning, stochastic optimization, and hybrid combinations of learning and optimization. Learning-based policies will be compared with equivalent rolling stochastic optimization benchmarks operating
-
Are you fascinated by how machine learning can enhance control without compromising safety or stability? As a PhD candidate, you will develop scalable methods for expressive and flexible neural
-
, including reinforcement learning, hierarchical models, Bayesian inference etc. More details of key responsibilities of this role, in addition to the essential and desirable job criteria, are available in