The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs

Published in International Conference on Learning Representations (ICLR), 2022

Recommended citation: Johannes Müller, Guido Montúfar. The Geometry of Memoryless Stochastic Policy Optimization in Infinite-Horizon POMDPs. International Conference on Learning Representations (ICLR) (2022). https://openreview.net/forum?id=A05I5IvrdL-