Gargi Vaidya
Papers
1
Total Citations
26
H-Index
1
About
Gargi Vaidya is a researcher advancing the frontiers of reinforcement learning (RL), with a particular focus on overcoming the challenge of sparse reward signals in complex, real-world environments. Her most cited work, "Reinforcement Learning with Sparse Rewards using Guidance from Offline Demonstration" (2022, 26 citations), addresses a critical bottleneck in RL: the lack of dense, carefully designed feedback. Vaidya’s key contribution lies in developing methods that leverage offline demonstration data to guide learning when only intuitive, binary reward functions are available—indicating task completion without fine-grained progress cues. This approach enables agents to learn effectively from minimal feedback, bridging the gap between theoretical RL and practical deployment. Her research has significant implications for robotics, autonomous systems, and any domain where reward engineering is prohibitively difficult. By tackling the sparsity problem head-on, Vaidya is helping to make RL more robust and applicable to real-world tasks, earning recognition for her innovative use of demonstration guidance to accelerate learning in data-scarce settings.
Research Focus
Key Achievements
Top Papers
- 1