Vaibhav Mathur
Papers
1
Total Citations
8
H-Index
1
About
Vaibhav Mathur is a rising researcher at the intersection of imitation learning, optimal transport, and reinforcement learning. His work addresses a fundamental challenge in artificial intelligence: how to efficiently learn complex decision-making policies from expert demonstrations. Mathur’s most notable contribution, "Watch and Match: Supercharging Imitation with Regularized Optimal Transport" (2022, 8 citations), introduces a novel framework that leverages regularized optimal transport to overcome the limitations of traditional inverse reinforcement learning (IRL). Instead of the computationally expensive, iterative process of inferring reward functions, Mathur’s approach directly aligns agent behavior with expert trajectories, dramatically improving learning efficiency and robustness. This work has been recognized for its potential to scale imitation learning to more complex, real-world tasks, offering a principled alternative to adversarial methods. By bridging optimal transport theory with practical imitation learning, Mathur is carving a path toward more sample-efficient and reliable autonomous systems, making his research essential reading for anyone interested in the future of robot learning and decision-making under uncertainty.
Research Focus
Key Achievements
Top Papers
- 1