Reinforcement Learning: Tabular Q-Learning
4 min
code
python
mdp
I’ve decided to start learning reinforcement learning with Frozenlake game and Q-Learning.
Dec 17, 2025
Gregor Cerar, PhD
Research & Inovation Engineer, Research Fellow
Hi 🖐️! I’m Gregor (Greg for short). I’m a Research & Innovation Engineer at Comsensus and a Postdoc / Professional Research Fellow at Jožef Stefan Institute, working with SensorLab.
Most of my time, I work in Python. I build backend services, data pipelines, and tools for working with energy systems, including problems like grid stability. I often work closely with power system experts, translating domain knowledge into practical software and services, and occasionally apply machine learning when it makes sense. I also work with Linux, containers, and Kubernetes.
My background is in wireless communications and AI (PhD in ICT).
I’m interested in time-series analysis, representation learning, and smart infrastructure – especially where theory meets practical systems.
Outside of work, I spend time with my family, hike, play chess, and the occasional game of Uno.
Thanks for stopping by!
Recent posts (All posts)
No matching items