Bharat Kesari
Papers
1
Total Citations
4
H-Index
1
About
Bharat Kesari is a researcher advancing the frontiers of reinforcement learning and robotics, with a focus on enabling efficient policy transfer across domains. His work tackles the critical challenge of reducing expensive interaction costs in robotic training, particularly through sim-to-real (Sim2Real) transfer. Kesari’s key contributions center on developing frameworks that allow robots to adapt learned behaviors from simulation to the real world with minimal data. His notable 2023 paper, “A Framework for Few-Shot Policy Transfer Through Observation Mapping and Behavior Cloning,” introduces a novel approach combining observation mapping and behavior cloning to achieve rapid policy adaptation, requiring only a handful of real-world demonstrations. This work has already garnered 4 citations, signaling its growing influence in the field. By addressing the prohibitive interaction costs that limit robotic deployment, Kesari’s research holds promise for making autonomous systems more practical and accessible. His achievements reflect a deep commitment to bridging the gap between simulated training environments and real-world application, paving the way for more efficient and scalable robotic learning.
Research Focus
Key Achievements
Top Papers
- 1