A plethora of problems in AI, engineering and the sciences are naturally formalized as inference in discrete probabilistic models.
In this paper, we propose an agent-based simulation tool, which is grounded in human cognition and decision-making, for evaluating and improving the effectiveness of building evacuation procedures and guidance systems during a disaster.
In this work, we introduce a new approach for the efficient solution of autonomous decision and planning problems, with a special focus on decision making under uncertainty and belief space planning (BSP) in high-dimensional state spaces.
Inference and decision making under uncertainty are key processes in every autonomous system and numerous robotic problems.
Deep reinforcement learning (DRL) algorithms have achieved great success on sequential decision-making problems, yet is criticized for the lack of data-efficiency and explainability.
This paper reviews recent advances in the field of optimization under uncertainty via a modern data lens, highlights key research challenges and promise of data-driven optimization that organically integrates machine learning and mathematical programming for decision-making under uncertainty, and identifies potential research opportunities.