Nilaksh Nilaksh

Indian Institute of Technology Kharagpur

Papers

Total Citations

H-Index

About

Nilaksh Nilaksh is a rising researcher at the forefront of reinforcement learning (RL), with a particular focus on making RL training safer, faster, and more scalable for real-world applications. His most-cited work, "Barrier Functions Inspired Reward Shaping for Reinforcement Learning" (2024, 10 citations), introduces a novel framework that leverages control-theoretic barrier functions to guide agent exploration and reward design. This approach addresses a critical bottleneck in modern RL: the long training times and safety risks associated with large state spaces. By moving beyond traditional value-function-based reward shaping, Nilaksh’s method offers a principled, scalable alternative that improves both learning efficiency and constraint satisfaction. His contributions are especially relevant for deploying RL in safety-critical domains like autonomous driving and robotics, where reward shaping must balance performance with strict operational boundaries. Though early in his career, Nilaksh’s work has already garnered attention for its elegant fusion of control theory and machine learning, marking him as a promising voice in the next wave of RL innovation. His research not only advances algorithmic foundations but also paves the way for more reliable, human-aligned autonomous systems.