We propose a modular reinforcement learning architecture for non-linear, nonstationary control tasks, which we call multiple model-based reinforcement learning (MMRL). The basic i...
riented programming, design patterns, and frameworks are abstraction techniques that have been used to reduce the complexity of sequential programming. This paper describes our ap...
Steve MacDonald, John Anvik, Steven Bromling, Jona...
Let R be the preorder of embeddability between countable linear orders colored with elements of Rado’s partial order (a standard example of a wqo which is not a bqo). We show tha...
In the presented paper, some issues of the fundamental classical mechanics theory in the sense of Ising physics are introduced into the applied neural network area. The expansion o...
nstrate how the respective architectural abstractions support increasingly complex application. Gerd Kortuem and Fahim Kawsar Lancaster University Daniel Fitton University of Centr...