Vignesh Gurumurthy
Papers
1
Total Citations
5
H-Index
1
About
Vignesh Gurumurthy is an emerging researcher in artificial intelligence, with a primary focus on reinforcement learning and its applications to complex control and optimization problems. His most-cited work, "An efficient reinforcement learning scheme for the confinement escape problem" (2024), introduces a novel algorithmic framework that significantly improves sample efficiency and convergence speed in environments with sparse rewards—a critical challenge in autonomous navigation and robotics. By designing a tailored reward-shaping mechanism and leveraging off-policy learning, Gurumurthy’s approach enables agents to escape confined spaces with minimal training data, achieving state-of-the-art performance in simulated benchmarks. This contribution has already garnered 5 citations, reflecting its immediate relevance to researchers tackling exploration-exploitation dilemmas. Beyond this flagship paper, his broader research explores scalable RL architectures and transfer learning, aiming to bridge the gap between simulated training and real-world deployment. Gurumurthy’s work is particularly notable for its practical orientation, offering solutions that are both theoretically sound and computationally feasible. As a rising voice in the RL community, his research holds promise for advancing autonomous systems in search-and-rescue, warehouse logistics, and beyond.
Research Focus
Key Achievements
Top Papers
- 1