Konstantin is Leading Researcher at the Artificial Intelligence Institute (AIRI) and holds the same position at the Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences (FRC CSC RAS). His research interests include heuristic search, planning, multi-agent systems, and integrating machine learning and search. He authored over 150 papers and 3 of his most cited papers are dedicated to multi-agent pathfinding (MAPF) and utilizing reinforcement learning (RL) for single-agent grid-based pathfinding. One of his main contributions to MAPF research is the use of Safe Interval Path Planning (SIPP) in MAPF solvers, which is a key part in many modern MAPF solvers. He also developed CCBS, an important variant of Conflict-Based Search (CBS) algorithm capable of handling arbitrary durations of the actions the agents might perform. Recently, he has been focusing on using RL/ML to solve decentralized variants of MAPF.
For more information visit kyakovlev.me.
Sven Koenig is Chancellor's Professor and Bren Chair at UC Irvine. Most of his research centers around techniques for decision-making (planning and learning) that enable single situated agents (such as robots or decision-support systems) and teams of agents to act intelligently in their environments and exhibit goal-directed behavior in real-time, even if they have only incomplete knowledge of their environment, imperfect abilities to manipulate it, limited or noisy perception or insufficient reasoning speed. Sven is a fellow of the Association for the Advancement of Artificial Intelligence (AAAI), the Association for Computing Machinery (ACM), the Institute of Electrical and Electronics Engineers (IEEE), and the American Association for the Advancement of Science (AAAS).
For more information visit idm-lab.org.
Guillaume Sartoretti joined the Mechanical Engineering Department at the National University of Singapore (NUS) as an Assistant Professor in 2019, where he founded the Multi-Agent Robotic Motion (MARMot) lab. Before that, he was a Postdoctoral Fellow in the Robotics Institute at Carnegie Mellon University (USA), where he worked with Prof. Howie Choset. He received his Ph.D. in robotics from EPFL (Switzerland) in 2016 for his dissertation on "Control of Agent Swarms in Random Environments," under the supervision of Prof. Max-Olivier Hongler. His passion and research lie in understanding and eliciting emergent coordination/cooperation in large multi-agent systems, by identifying what information and mechanisms can help agents reason about their individual role/contribution to each other and to the team. Guillaume was a Manufacturing Futures Initiative (MFI) postdoctoral fellow at CMU in 2018-2019, was awarded an Amazon Research Awards in 2022, as well as an Outstanding Early Career Award from NUS' College of Design and Engineering in 2023.
For more information visit marmotlab.org
Currently, Aleksandr leads a Cognitive AI Agents lab at the Artificial Intelligence Institute (AIRI), engages in embodied artificial intelligence at the Cognitive Modeling Center and works on deep reinforcement learning at the Russian Academy of Sciences. His current scientific interests relate to the transformer and structured world models in reinforcement learning, applying language models for behavior planning (including robotics platforms), multi-agent planning and learning, and indoor visual navigation. In 2019, he led the CDS team, which took first place in the NeurIPS MineRL competition. In 2023, he led the SkillFusion team, which secured first place in the CVPR Habitat competition.
For more information visit grafft.github.io.
Аlexey Skrynnik is a Research Scientist with a PhD in Computer Science, specializing in Artificial Intelligence and Machine Learning. His focus on applied Reinforcement Learning and Multi-Agent Systems has led to significant contributions, particularly in decentralized multi-agent pathfinding. Alexey has introduced advanced RL algorithms such as Follower, MATS-LP, and Switcher and developed the POGEMA environment, which has become a key benchmark for these techniques. In addition to his work on multi-agent systems, Alexey's research in hierarchical RL has made waves, especially through his development of the ForgER approach. This method propelled his team to a first-place finish in the NeurIPS 2019 MineRL Diamond competition, showcasing his ability to excel in competitive research environments. Furthermore, he's been leading efforts to combine NLP with RL to improve language-driven task solving, highlighted by his role in directing the RL track of the IGLU competition at NeurIPS 2021/2022
For more information visit tviskaron.github.io.
Anton Andreychuk is a Research Scientist with a Ph.D. in Computer Science. His main research interests are heuristic search algorithms and multi-agent pathfinding. His results have been presented at the leading AI conferences, including IJCAI, AAAI, AAMAS, and ICAPS.