Irma Ravkic

About

Irma Ravkic is a researcher whose work sits at the intersection of artificial intelligence, probabilistic programming, and relational machine learning. Her primary research focus is on developing models that can reason effectively under uncertainty, particularly in complex, hybrid domains that combine both discrete and continuous variables. Ravkic’s most notable contribution is her pioneering work on dynamic hybrid relational models, where she introduced novel approaches for learning the structure of relational Markov decision processes (MDPs) without requiring the discretization of continuous variables. This work, published in 2016 and garnering 11 citations, advances the field by enabling more accurate and scalable inference in probabilistic programs. Her research has significant implications for robotics, automated planning, and decision-making systems that must operate in real-world environments. By bridging the gap between discrete symbolic reasoning and continuous state spaces, Ravkic has helped lay the groundwork for more robust AI systems. Her contributions are particularly valuable for students and researchers interested in probabilistic modeling, reinforcement learning, and the challenges of scaling AI to hybrid, dynamic settings.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning the Structure of Dynamic Hybrid Relational Models

   11 citations · 2016

Key Collaborators

Contact & Links