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
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.
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