Sayak Mukherjee
Papers
3
Total Citations
13
H-Index
2
About
Sayak Mukherjee is a researcher specializing in multi-agent reinforcement learning, distributed control systems, and autonomous robotics, with a particular focus on applying these methods to complex real-world challenges. His work bridges the gap between theoretical machine learning and practical deployment in cyber-physical systems, making meaningful contributions to both fields. Among his most recognized contributions is "AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning" (2022, 7 citations), which advances autonomous multi-robot coordination for search and rescue missions in remote and challenging environments. This work addresses the intricate balance between local single-robot control, group primitives, and global mission coordination — a significant step forward for real-world autonomous systems. Mukherjee has also made notable strides in distributed model-free reinforcement learning, tackling the critical and often overlooked problem of stability guarantees in learning-based control frameworks. His research on scalable decision-making for cyber-physical systems — spanning smart transportation, robotic swarms, and power systems — addresses fundamental limitations in existing learning paradigms. Though early in citation accumulation, his work lays important theoretical groundwork that is increasingly relevant as autonomous systems become more prevalent across industries.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3