Reinforcement learning as a basis for cross domain fusion of heterogeneous data

Christensen, SörenTomforde, Sven2022-09-092022-09-0920222022http://dx.doi.org/10.1007/s00287-022-01468-xhttps://dl.gi.de/handle/20.500.12116/39365We propose to establish a research direction based on Reinforcement Learning in the scope of Cross Domain Fusion. More precisely, we combine the algorithmic approach of evolutionary rule-based Reinforcement Learning with the efficiency and performance of Deep Reinforcement Learning, while simultaneously developing a sound mathematical foundation. A possible scenario is traffic control in urban regions.Reinforcement learning as a basis for cross domain fusion of heterogeneous dataText/Journal Article10.1007/s00287-022-01468-x1432-122X