Abhishek Kulkarni

Papers

Total Citations

H-Index

About

Abhishek Kulkarni is an emerging researcher working at the intersection of reinforcement learning, formal methods, and automated curriculum design. His most notable work, "Automaton-Guided Curriculum Generation for Reinforcement Learning Agents" (2023), addresses one of the most persistent challenges in the field: the prohibitive computational cost and impracticality of learning complex sequential decision-making tasks. By leveraging logical task specifications to automatically generate reward functions and guide curriculum learning, Kulkarni's research offers a principled framework for making reinforcement learning agents more scalable and efficient in tackling structured, long-horizon problems. This contribution bridges the gap between symbolic reasoning and modern deep reinforcement learning, an area of growing importance as AI systems are deployed in increasingly complex real-world environments. Although his work is at an early stage with 4 citations, it addresses a fundamental bottleneck that has captured significant attention from the broader AI and robotics communities. Kulkarni's research trajectory suggests a promising career at the forefront of neurosymbolic AI and specification-driven learning, areas poised to play a critical role in developing robust, interpretable autonomous systems.