A Bayesian Learning Framework

    I particularly like the premise here ... that the approach starts with causal decision descriptions of the real world.  With the potential of building from real world process.   Often use 'influence diagrams' to do this.  Or existing process models.  Sounds like there could be a means to iterate between real world and model.  And converge?

In Technology Review:
" ... The researchers used a technique they call the Bayesian program learning framework, or BPL. Essentially, the software generates a unique program for every character using strokes of an imaginary pen. A probabilistic programming technique is then used to match a program to a particular character, or to generate a new program for an unfamiliar one. The software is not mimicking the way children acquire the ability to read and write but, rather, the way adults, who already know how, learn to recognize and re-create new characters.

“The key thing about probabilistic programming—and rather different from the way most of the deep-learning stuff is working—is that it starts with a program that describes the causal processes in the world,” says Tenenbaum. “What we’re trying to learn is not a signature of features, or a pattern of features. We’re trying to learn a program that generates those characters.”  .... '