Kira Mour

Papers

Total Citations

H-Index

About

Kira Mour is a researcher at the intersection of artificial intelligence, automated planning, and machine learning, with a particular focus on learning action models for planning systems. Her most cited work, "Using Kernel Perceptrons to Learn Action Effects for Planning" (2008, 18 citations), makes a foundational contribution by introducing a kernel perceptron-based approach to automatically infer action effects in STRIPS and ADL planning domains. This work addresses a critical bottleneck in AI planning—the manual specification of action models—by encoding action and state information into compact vector representations and learning state changes directly from experience. Mour's approach demonstrates how machine learning techniques can be effectively integrated into symbolic planning frameworks, enabling systems to adapt and improve their knowledge of action dynamics over time. While her citation count reflects the specialized nature of her work, her contributions are significant for advancing the practical deployment of planning systems in dynamic environments where complete domain knowledge is unavailable. Mour's research exemplifies the growing synergy between learning and reasoning in AI, offering valuable insights for students and researchers working on automated planning, reinforcement learning, and intelligent agent design.