The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes
Published in Proceedings of the 43rd International Conference on Machine Learning (ICML 2026), 2026
Recommended citation: Anderson, R. A., & Montúfar, G. (2026). "The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes." Proceedings of the 43rd International Conference on Machine Learning (ICML 2026). https://openreview.net/forum?id=l94JabCBGL
We study the geometry of the space of value functions in partially observable Markov decision processes (POMDPs), showing that it forms a semi-algebraic set, and we use tools from real algebraic geometry to characterize its structure.