MrOmar Adalat

Research Postgraduate

Department of Computing - Faculty of Engineering

RESEARCH

Primarily, I am interested in safe and verifiable multi-agent reinforcement learning as part of my PhD.

 

More broadly, my research interests contain the following:

  • Logical formalisms for Verification & Specification, including quantitative and probabilistic formalisms
  • Safe Reinforcement Learning
  • Knowledge Representation and Reasoning
  • Formal methods
  • Reasoning about Actions and Automated Planning + Scheduling
  • Multiagent Systems and Game Theoretic Dynamics
  • Neurosymbolic AI (e.g. logic & learning)
  • Explainability (XAI) and Interpretability
  • Reactive Synthesis
  • Causality