Abhishek Naik

Papers

Total Citations

H-Index

About

Abhishek Naik is a researcher whose work lies at the intersection of reinforcement learning, imitation learning, and risk-aware decision-making. His most notable contribution, "RAIL: Risk-Averse Imitation Learning," introduces a novel framework that extends Generative Adversarial Imitation Learning (GAIL) to account for risk sensitivity. While GAIL learns policies by mimicking expert trajectories, Naik’s RAIL algorithm explicitly incorporates risk aversion, enabling agents to avoid catastrophic failures in safety-critical domains such as autonomous driving or healthcare. This work, though early in its citation trajectory with 4 citations, has laid a foundation for integrating risk metrics into imitation learning—a growing area of interest. Naik’s research addresses a key limitation of standard imitation learning: its assumption of risk-neutral behavior. By developing algorithms that balance performance with safety, he contributes to making AI systems more robust and trustworthy. His work is particularly relevant for students and researchers exploring how to bridge the gap between theoretical reinforcement learning and real-world deployment, where uncertainty and risk are unavoidable.