Skip to content Search

The team conducts research in areas integrating reinforcement learning and graph neural networks

The core area of use for the concepts we are developing is the energy system, in particular its design, control and automated energy trading.

We analyse trading in the cyclical market as a sequential decision-making process. An entity participating in a trade issues buy and sell orders. These orders should be determined on the basis of all information which shapes the current market situation and the situation of the trading entity. How to transform this information into orders in a manner that will bring the highest benefit to the entity? We design reinforcement learning algorithms that optimize strategies for determining orders based on market data.

The team develops neural networks that generate graphs. These solutions are oriented towards the automatic design of structures naturally represented by graphs, such as molecules or energy networks. Known methods for generating graphs are based on an assumed limitation on the size of the graph and are thus not scalable. How to generate arbitrarily large graphs that meet set functional requirements? We are developing methods that address this challenge.

While combining reinforcement learning and graph neural networks, we are working on reinforcement learning methods for multiple agents connected by graph-structured links. These methods are oriented towards optimising the control of devices in a system such as a power grid, such as distributed energy storage. We are looking for answers to the challenges of the ongoing energy transformation. More and more electrical energy is coming from weather-dependent sources, i.e. windmills and solar panels, which is desirable due to the promotion of renewable energy, but significantly impedes the controlling of the grid.

Research Team Leader


Paweł Wawrzyński

Paweł Wawrzyński, MSc, Eng, PhD, DSc has been associated with IDEAS NCBR since 2023. In the years 2016-2022, he worked at the Institute of Computer Science, Warsaw University of Technology, where he served as the Deputy Director for Research. Between 2005 and 2016, he worked at the Institute of Automation and Applied Informatics of the Warsaw University of Technology. He has authored more than 50 scientific publications, including in the journals such as ‘Neural Networks’, ‘IEEE Transactions on Neural Networks and Learning Systems’ and post-conference publications of the International Joint Conference on Artificial Intelligence (IJCAI). He holds four patents and is the author of five pending patent applications. Furthermore, he has managed investments, has been an economic journalist and has funded or co-funded three technology start-ups.

Pawel Wawrzyński’s research interests include machine learning and its practical applications. The areas of his theoretical research are in particular reinforcement learning, graph neural networks and continual learning. He implements his research results in marketing, robotics, automotive and energy industries.

Other research groups and teams

  • Sequential Decision Making We believe that the development of techniques for effective analysis and decision-making in sequences will lead to the creation of intelligent and autonomous systems. This will translate into many practical solutions, ranging from controlling robots or autonomous vehicles to multi-step decision or deductive procedures, such as mathematical proofs.
    Piotr Miłoś
  • Learning in Control, Graphs and Networks The team develops neural networks that generate graphs. These solutions are oriented towards the automatic design of structures
    Paweł Wawrzyński
  • Algorithms in Autonomous UAVs Unmanned aerial vehicles (UAVs), also commonly known as drones, are becoming increasingly common in various aspects of life.
    Przemysław Kornatowski