Policy Gradients in the Complex Plan
https://substack.com/@mohamedelwardi/note/p-199676741?r=294n7j&utm_source=notes-share-action&utm_medium=web
#ReinforcementLearning #HumbleSystemsTheory #ArtificialIntelligence
A Natural Gradients Algorithm for Complex-Valued Reinforcement Learning under Humble Systems Theory
FellowIPS777