Sahisnu Mazumder

Central Mechanical Engineering Research Institute

Papers

Total Citations

H-Index

About

Sahisnu Mazumder is a researcher whose early work laid the groundwork in reinforcement learning and autonomous systems. His most-cited paper, "Application of single agent Q-learning for light exploration" (2010, 3 citations), introduced a novel application of Q-learning—a subset of reinforcement learning—to enable mobile robots to autonomously explore and respond to light sources. This foundational contribution demonstrated how machine learning algorithms could systematically evolve robot behaviors based on real-world data, bridging the gap between theoretical AI and practical robotics. While his citation count reflects the niche, early-stage nature of this work, it underscores his role in advancing adaptive learning for autonomous agents. Mazumder’s research interests span reinforcement learning, intelligent systems, and the integration of machine learning into robotics. His work has contributed to the broader understanding of how single-agent learning frameworks can be applied to complex environmental tasks, inspiring subsequent studies in autonomous navigation and sensor-based exploration. For students and researchers, Mazumder’s early exploration of Q-learning in robotics offers a clear example of how foundational algorithms can be adapted for real-world challenges, highlighting the iterative process of innovation in AI-driven autonomous systems.