Overview
Learn about planning fundamentals in sequential decision-making through a 19-minute lecture that explores how agents discover and implement solutions in both ideal and real-world scenarios. Dive into the process of identifying optimal actions that lead to and maintain favorable states, while understanding the computational complexities involved in stochastic environments. Examine key factors affecting solution optimization, including branching factors and search tree depth, and discover strategies for improving planning algorithm efficiency through structural properties like compositionality, productivity, and localism.
Syllabus
RobotLearning: Sequential Decision Making, part 2
Taught by
Montreal Robotics