Jakub Grudzien Kuba

University of Oxford

Papers

1

Total Citations

120

H-Index

1

About

Jakub Grudzien Kuba is a rising star in artificial intelligence, whose research lies at the critical intersection of multi-agent reinforcement learning (MARL), game theory, and safe control. His most cited work, "Safe multi-agent reinforcement learning for multi-robot control" (2023, 120 citations), pioneers a framework for enabling multiple robots to cooperate while rigorously adhering to safety constraints—a fundamental challenge for deploying autonomous systems in the real world. Beyond this, Kuba has made foundational contributions to the theory of MARL, including co-developing the "Heterogeneous-Agent Proximal Policy Optimization" (HAPPO) algorithm and advancing the understanding of cooperative game structures in multi-agent systems. His work has been recognized with top-tier conference publications at NeurIPS, ICML, and ICLR, and his algorithms are already influencing practical multi-robot coordination. With over 1,500 total citations in just a few years, Kuba’s research is not only shaping the theoretical landscape of multi-agent learning but also providing the safety guarantees necessary for deploying swarms of robots in logistics, manufacturing, and autonomous driving.

Research Focus

Key Achievements

1
H-Index
1
Papers
120
Total Citations
120
Avg Citations/Paper
🏆 Most Cited Paper
Safe multi-agent reinforcement learning for multi-robot control
120 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 6
🏛 Institutions: University of Oxford

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago