Smart Analytics &
Reinforcement Learning

Exploring cutting-edge AI applications from theoretical research to industry solutions at PLUS University Salzburg.

Research Areas & Projects

Our team drives innovation through funded research projects and fundamental studies in:

INSPIRE

Intelligent Novel Support for Personalised Instruction and Robust Evaluation in STEM

A research cooperation with Salzburg University of Teacher Education. Developing AI support for personalized STEM education.

WISS2030 Funded

FOCUS

Forecasting and Optimisation for Sustainable Industrial Energy Systems

Research cooperation with COPA-DATA GmbH to optimize industrial energy usage under constraints and uncertainty.

Industry Partner

RL for Particle Accelerators

Collaborations with CERN, GSI, and others to apply Reinforcement Learning for the control and optimization of particle accelerators.

CERN / GSI

Multivariate Time Series

Developing novel approaches for analyzing complex temporal data patterns and trends across multiple variables.

Bayesian Methods

Applying probabilistic modeling and Bayesian inference to handle uncertainty and incorporate prior knowledge.

Human-AI Integration

Creating synergistic systems that combine human expertise with artificial intelligence capabilities.

Our Team

Meet the researchers and academics driving innovation in reinforcement learning:

Simon Hirlaender

Simon Hirlaender

Team Lead, Reinforcement Learning and Smart Analytics

Leading the SARL team's research initiatives in reinforcement learning applications and interdisciplinary AI projects.

Sabrina Pochaba

Sabrina Pochaba

PhD Student

Multi-Agent Reinforcement Learning for Resource Allocation in Wireless Network Communication.

Sarah Trausner

Sarah Trausner

PhD Student

FOCUS: Forecasting and optimization under constraints and uncertainty for sustainable industrial energy systems.

Christoph Schranz

Christoph Schranz

PhD Student

Contactless Monitoring Beyond Ballistocardiography.

Reuf Kozlica

Reuf Kozlica

PhD Student

Hierarchical reinforcement learning in assembly line optimization.

Georg Schaefer

Georg Schaefer

PhD Student

Improving Trajectory Tracking by Augmenting States with Future Targets.

Markus Dygruber

Markus Dygruber

PhD Student

INSPIRE: Intelligent Novel Support for Personalized Instruction and Robust Evaluation in STEM.

Olga Mironova

Olga Mironova

Master Student

Causal GP-MPC: Where Structure, Safety, and Online Learning Meet.

Benjamin Halilovic

Benjamin Halilovic

Master Student

Robust Real-Time Optimization of SIS18 Injection using Gaussian Process MPC.

Julian Langschwert

Julian Langschwert

Master Student

Online Parameter Identification via RL Integrated with Model Predictive Control.

Sahan Dabarera

Sahan Warnakulasooriya Dabarera

Master Student

Adaptive PID Tuning via Meta-Reinforcement Learning.

Laya Shibu Xavior

Laya Shibu Xavior

Master Student

Regelungsoptimierung von Piezoantrieben.

Announcements & Upcoming Events

More Announcements

  • 2026 Podcast: "Wie Reinforcement Learning Unternehmen verändert" — DIH West / Spotify Listen
  • 2026 IPAC 2026: 4 posters on Causal GP-MPC, Koopman World Models, SIS18 GP-MPC, and RL Beyond Greedy Details
  • January 2026 INSPIRE Project Launched: AI for personalized STEM education Learn More
  • October 2025 Keynote at zenonIZE 2025: Future of AI-driven automation Learn More

Recent Publications

Selected recent works from our team (2024-2026):

RL Beyond Greedy Optimisation for Delayed-Consequence Accelerator Control

Tengler, M., Bjoerkbom, K., Hirländer, S., et al.

IPAC'26 (2026)

Causal GP-MPC: Where Structure, Safety, and Online Learning Meet

Mironova, O., Hirländer, S., et al.

IPAC'26 (2026)

Robust Real-Time Optimization of SIS18 Injection using Gaussian Process MPC

Halilovic, B., Appel, S., Hirländer, S., et al.

IPAC'26 (2026)

Koopman-Stabilised World Models for Offline Reinforcement Learning

Hirländer, S., et al.

IPAC'26 (2026)

Reinforcement Learning in Particle Accelerators

García, A. S., Xu, C., Eichler, A., Kaiser, J., & Hirländer, S.

IPAC'25 (2025)

Python-Based Reinforcement Learning on Simulink Models

Schäfer, G., Huber, S., Hirländer, S., et al.

Machine Learning and Knowledge Discovery in Databases (2024)

Multi-agent Reinforcement Learning and Its Application to Wireless Network Communication

Pochaba, S., Kwitt, R., Hirländer, S., et al.

Machine Learning and Knowledge Discovery in Databases (2024)

Deep Meta Reinforcement Learning for Rapid Adaptation In Linear Markov Decision Processes: Applications to CERN's AWAKE Project

Hirländer, S., Pochaba, S., Xu, C., et al.

Machine Learning and Knowledge Discovery in Databases (2024)

The Reinforcement Learning for Autonomous Accelerators Collaboration

Santamaría, A., Xu, C., Scomparin, L., Hirländer, S., Pochaba, S., et al.

IPAC'24

Contact Us

Visit Us

Address:

IDA Lab Salzburg
Fachbereich Artificial Intelligence & Human Interfaces (AIHI)
Fakultät Digital & Analytical Sciences (DAS)
Paris Lodron Universität Salzburg (PLUS)
Jakob-Haringer-Straße 6 | Techno 6 | 5020 Salzburg | Austria

IDA Lab Salzburg (SARL Team)
Jakob-Haringer-Straße 6 | Techno 6 | 5020 Salzburg | Austria