We are a team of researchers and students at Czech Technical University in Prague (CTU), focusing mainly on applied research in artificial intelligence, machine learning and multi-agent systems. Our team is a part of a bigger group called Artificial Intelligence Center (AIC).
Our scientific expertise has applications in two specific areas: Computer Game AI and Simulation Modeling. Methodologies, approaches and algorithms at our disposal can often be applied to overlapping (although seemingly different) challenges from these two problem areas.
In addition to academic research, we organize educational events to attract young talents into AI research, we seek to accelerate the transfer of scientific knowledge into practice, and offer our insight to public sector institutions in order to improve the quality of life in urban areas.
Applications of Machine Learning techniques (incl. Reinforcement Learning and Inverse RL) to implement a human-level AI player of real-time strategy games. Development of open-source tools that make this easier for research community.
Opponent Modeling solutions combining machine learning methods with expert knowledge to infer and predict opponent's actions. Released as an open-source library for StarCraft: Brood War bots.
A bot for StarCraft: Brood War that serves as a testbed for AI methods we currently deal with during our research (e.g. Inverse Reinforcement Learning, Deep RL, MAS or Genetic Algorithms).
We're organizing a 24/7 educational event, serving as a challenging competitive environment for hundreds of AI students and researchers. Participants submit bots programmed in C++ or Java to play 1v1 StarCraft matches.
We build and maintain a large-scale, data-driven, multi-agent model of urban population. Compared to traditional approaches, the high level of detail provided by data-driven agent-based models enables answering a wider range of what-if questions, including the impact of infrastructure developments, adoption of new mobility and transport policies or changes in mobility services available.
We study algorithms for demand-responsive transport schemes using our agent-based simulation and benchmarking testbed. It can simulate and evaluate a wide variety of centralized and distributed coordination or resource allocation mechanisms and is avaliable for public as an open source project.
We develop software systems for automated collection, annotation and processing of data about the movement and activities of urban population. Collected information is meant to replace surveys and questionnaires as the input for data-driven mobility models.
Based on our models, simulations and collected data, we prepare extensible analyses, reports and visualizations for a variety of public sector institutions and private companies. For this purpose, we have founded a spin-off company called Urban Algorithmics.
Announcement: We've just published StarCraft: Brood War docker images!
This means the end of complicated game setup for newcomers, or people who would like to simply play SC1 games against AI bots.
You can also develop your bots on your favorite platform instead of relying on Windows. There are still many things to do, and we will be working on improvements.
We have more things cooking: It is a part of our ongoing effor to create environment for reinforcement...
As of today, we're launching the website and blog of Games and Simulations research group at this url: http://gas.fel.cvut.cz/. We will try to announce the relevant (and sometimes irrelevant) news here in a blogpost form and keep the list of projects more or less up-to-date.
Feel free to contact any of us if you find something we do interesting. We're always open to cooperation and feedback.
This is the current list of core group members, directly affiliated with CTU. Note that we do not explicitly mention multiple external or short-term collaborators, or even our close colleagues, who hold more important roles in different groups at CTU.