Lifelong Formal Modeling Agents -- Definitions and Implementation Strategies

Jacques Basaldúa

Keywords: NLP, reinforcement learning, lifelong learning, code generation

TL;DR: A description of our work towards building lifelong learning agents that learn to formalize (i.e, generate code that can be evalauted).

Abstract:

This paper summarizes the current vision and results of our research since 2016, the beginning of our Jazz platform project.
We explain the design of Lifelong Formal Modeling Agents by starting with describing and defining basic ideas and discussing
their importance.

We present a complete architecture built upon these ideas, summarize our experimental results where available and discuss
how they represent minimum requirements towards building reliable human understandable AI agency. Finally, we briefly touch on how
these agents could produce more natural human-computer interfaces.

It should be noted that the definitions presented in this paper of intelligence, understanding, concept, object, symbol and other
terms are intended for practical implementation and will not completely align with other academic definitions of the same terms.