Descripción
|
|
---|---|
Four principal features of autonomous control systems are left both unaddressed and unaddressable by present-day engineering methodologies: (1) The ability to operate effectively in environments that are only partially known at design time; (2) A level of generality that allows a system to re-assess and re- define the fulfillment of its mission in light of unexpected constraints or other un- foreseen changes in the environment; (3) The ability to operate effectively in en- vironments of significant complexity; and (4) The ability to degrade gracefully? how it can continue striving to achieve its main goals when resources become scarce, or in light of other expected or unexpected constraining factors that im- pede its progress. We describe new methodological and engineering principles for addressing these shortcomings, that we have used to design a machine that becomes increasingly better at behaving in underspecified circumstances, in a goal-directed way, on the job, by modeling itself and its environment as expe- rience accumulates. The work provides an architectural blueprint for construct- ing systems with high levels of operational autonomy in underspecified circum- stances, starting from only a small amount of designer-specified code?a seed. Using value-driven dynamic priority scheduling to control the parallel execution of a vast number of lines of reasoning, the system accumulates increasingly useful models of its experience, resulting in recursive self-improvement that can be au- tonomously sustained after the machine leaves the lab, within the boundaries im- posed by its designers. A prototype system named AERA has been implemented and demonstrated to learn a complex real-world task?real-time multimodal dia- logue with humans?by on-line observation. Our work presents solutions to sev- eral challenges that must be solved for achieving artificial general intelligence. | |
Internacional
|
Si |
DOI
|
10.1007/978-3-319-09274-4_9 |
Edición del Libro
|
|
Editorial del Libro
|
Springer International Publishing |
ISBN
|
978-3-319-09273-7 |
Serie
|
Lecture Notes in Computer Science |
Título del Libro
|
Artificial General Intelligence |
Desde página
|
85 |
Hasta página
|
96 |