Summary
Nishanth Vemgal is a Ph.D. researcher at McGill University and Mila with a decade of experience building novel continual reinforcement learning algorithms inspired by neuroscience, including publications at NeurIPS and ICML. He developed a value-decomposition framework separating permanent and transient components to speed adaptation in non-stationary environments and introduced Preferential Temporal Difference Learning for efficient estimation under partial observability. Beyond research, he co-instructs graduate RL courses, co-supervises theses, and led the mentorship-driven AIF-GEN project that produced an ICML workshop paper, demonstrating a blend of technical leadership and community building. His industry background in deploying RL and anomaly-detection systems at Fractal Analytics gives him a practical bent for taking research ideas toward real-world impact.
10 years of coding experience
4 years of employment as a software developer
Bachelor of Engineering (BE) Telecommunications Engineering, Bachelor of Engineering (BE) Telecommunications Engineering at PES University
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at McGill University
English, Kannada, Telugu, Hindi