Leslie Pack
Papers
1
Total Citations
5
H-Index
1
About
Leslie Pack is a pioneering researcher in artificial intelligence, specializing in the intersection of relational learning, probabilistic modeling, and automated planning. Her most-cited work, "Learning and Planning with Probabilistic Relational Rules" (2004, with 5 citations), introduces a framework that enables agents to autonomously learn action dynamics from experience and then leverage those models to generate robust plans for diverse goals. This contribution is foundational for developing AI systems that can operate in complex, uncertain environments—such as simulated blocks-world domains—where traditional rule-based planning falls short. Pack’s research bridges the gap between machine learning and planning, demonstrating how probabilistic relational rules can capture both structure and uncertainty. Her work has influenced subsequent advances in relational reinforcement learning and probabilistic planning, earning recognition for its clarity and practical impact. By showing how agents can learn world models and plan effectively, Pack has helped shape modern approaches to intelligent decision-making in robotics and interactive AI.
Research Focus
Key Achievements
Top Papers
- 1Learning and Planning with Probabilistic Relational Rules5 citations · 2004