Colin Graber

Papers

Total Citations

H-Index

About

Colin Graber is a researcher whose work lies at the intersection of natural language processing, robotics, and machine learning, with a focus on developing agents that can communicate, learn, and solve problems in grounded, interactive environments. His most cited work, the 2017 paper "Towards Problem Solving Agents that Communicate and Learn," co-authored with a team including Anjali Narayan-Chen and Dan Roth, addresses the challenge of creating agents that can understand language and act in physical or simulated worlds. This foundational paper, with 9 citations, explores how agents can learn from human instructions and feedback, bridging the gap between linguistic understanding and task execution. Graber's contributions are notable for advancing the integration of language grounding with reinforcement learning and planning, enabling more robust human-robot interaction. His work has implications for assistive robotics, autonomous systems, and interactive AI, where agents must dynamically interpret and respond to natural language. As a researcher, Graber is recognized for his role in shaping early efforts to build communicative, learning-driven problem solvers, laying groundwork for subsequent advances in grounded language acquisition and embodied AI.