Chandramouli Rajagopalan
Papers
1
Total Citations
2
H-Index
1
About
Chandramouli Rajagopalan is a researcher at the forefront of reinforcement learning (RL) and robotics, specializing in bridging the gap between data-efficient algorithms and real-world deployment. His work centers on model-based RL, particularly offline world models, aiming to reduce the extensive interaction time required for training robots. In his notable 2023 paper, "Finetuning Offline World Models in the Real World," Rajagopalan tackles the challenge of data inefficiency in RL by proposing methods to finetune pre-trained offline models with minimal real-world interaction. This contribution addresses a critical bottleneck in robotics, where hours or days of training are typically needed. Although his most-cited paper currently has 2 citations, it reflects an emerging and impactful direction in the field. Rajagopalan’s research is pivotal for advancing sample-efficient learning, making RL more practical for autonomous systems. His work is particularly relevant for students and researchers exploring offline RL, sim-to-real transfer, and robotics, offering a pathway to more efficient and scalable AI systems.
Research Focus
Key Achievements
Top Papers
- 1Finetuning Offline World Models in the Real World2 citations · 2023