Divyansh Garg
Papers
1
Total Citations
3
H-Index
1
About
Divyansh Garg is a leading researcher at the intersection of reinforcement learning, robotics, and language-guided decision-making. His work focuses on developing algorithms that enable agents to learn structured, interpretable behaviors from natural language instructions, addressing fundamental challenges in multi-task generalization and sample efficiency. Garg is best known for LISA (Learning Interpretable Skill Abstractions from Language), a pioneering framework that learns reusable skill abstractions from language descriptions, allowing policies to generalize more effectively across complex tasks. This work has garnered significant attention, with over 3 citations in its first year, and has influenced subsequent research in language-conditioned robotics. His contributions advance the goal of building AI systems that can understand and execute human instructions in dynamic environments, bridging the gap between high-level language and low-level control. Garg's research is particularly notable for its emphasis on interpretability and compositional generalization, making his work highly relevant for students and researchers interested in hierarchical reinforcement learning, skill discovery, and human-AI interaction.
Research Focus
Key Achievements
Top Papers
- 1LISA: Learning Interpretable Skill Abstractions from Language3 citations · 2022