Anthony R. Cassandra

Papers

Total Citations

1,198

H-Index

About

Anthony R. Cassandra is a pioneering researcher in artificial intelligence and robotics, best known for his foundational work on decision-making under uncertainty. His key research areas include partially observable Markov decision processes (POMDPs), reinforcement learning, and probabilistic robotics. Cassandra’s major contributions center on developing scalable algorithms for learning and planning in partially observable environments, where agents must act based on incomplete or noisy information. His seminal 1995 paper, “Learning policies for partially observable environments: Scaling up,” has garnered over 660 citations, establishing a framework for efficient policy learning in complex domains. In his highly cited 2002 work on mobile-robot navigation, he introduced discrete Bayesian models to handle uncertainty, demonstrating the optimal solution to action selection via POMDPs—a problem that had remained largely unexplored. This work has profoundly influenced autonomous robotics and decision theory. Additionally, his 1994 paper on optimal policies for POMDPs laid theoretical groundwork for model-based planning. Cassandra’s research has bridged theory and practice, enabling robots to navigate and act intelligently in uncertain real-world settings, making him a key figure in advancing AI’s ability to operate under ambiguity.