Shakti Singh
Papers
2
Total Citations
102
H-Index
2
About
Shakti Singh is a leading researcher in multi-agent systems and reinforcement learning, with a primary focus on autonomous target localization. Her work addresses the critical challenge of enabling teams of mobile sensing agents—such as UAVs and robots—to collaboratively and efficiently locate targets in complex environments. Singh’s major contributions lie in developing advanced multi-agent deep reinforcement learning frameworks that significantly improve coordination and learning efficiency. Notably, her 2022 paper, "Target localization using Multi-Agent Deep Reinforcement Learning with Proximal Policy Optimization," has garnered 68 citations, demonstrating its substantial impact on the field. She further advanced this work in 2023 with "Multiagent Deep Reinforcement Learning With Demonstration Cloning for Target Localization" (34 citations), which introduced a novel technique to accelerate learning by incorporating expert demonstrations. Through these innovations, Singh has pioneered methods that overcome the limitations of traditional stationary sensor systems, enabling more adaptive and scalable solutions for real-world search and surveillance missions. Her research continues to shape the future of autonomous multi-agent coordination and sensing.
Research Focus
Key Achievements
Top Papers
- 1
- 2