Owais Ahmed Malik

Papers

Total Citations

H-Index

About

Owais Ahmed Malik is an emerging researcher whose work sits at the intersection of reinforcement learning, autonomous robotics, and open-world machine learning. His research focuses on equipping intelligent systems with the ability to navigate complex, real-world environments and recognize previously unseen categories — two of the most challenging frontiers in modern artificial intelligence. Malik's most cited contribution, a 2022 comparative study of Deep Q-Learning, Q-Learning, and SARSA for robot local navigation, has garnered 6 citations and provides practitioners with valuable benchmarking insights for selecting reinforcement learning strategies in autonomous systems. Building on this foundation, his 2023 work on mapless crowd navigation introduces a novel Collision Probability metric into deep reinforcement learning frameworks, directly addressing critical limitations in generalization and scalability that hinder real-world robot deployment. Perhaps most ambitiously, his 2024 research advances unsupervised open-world recognition — tackling the difficult problem of training models to identify and continually learn unknown classes without labeled data, pushing beyond the constraints of classical supervised paradigms. Though early in his career with a growing citation record, Malik's portfolio demonstrates a coherent and forward-looking research vision centered on building more adaptable, robust, and practically deployable intelligent systems.