Shauharda Khadka

Papers

Total Citations

H-Index

About

Shauharda Khadka is a researcher at the forefront of multi-agent reinforcement learning and adaptive robotics. His work centers on enabling teams of autonomous agents—from terrestrial robots to extraterrestrial explorers—to learn and adapt collaboratively in dynamic, real-world environments. Khadka’s key contribution lies in integrating memory mechanisms into multi-robot systems, allowing teams to form joint strategies that respond to novel observations and changes in teammates’ behavior. His seminal paper, “Memory-augmented multi-robot teams that learn to adapt” (2017), has garnered 2 citations, laying foundational groundwork for adaptive, memory-driven coordination. Beyond this, Khadka’s research pushes the boundaries of how machines learn to cooperate, with implications for factories, homes, and space exploration. His work is notable for bridging deep reinforcement learning with practical multi-agent challenges, earning recognition for its potential to transform autonomous systems. For students and researchers, Khadka exemplifies how memory and adaptation can unlock more resilient, intelligent robot teams.