BoundedSeedAGI_agi14 - Bounded Seed-AGI Eric Nivel1...

Info icon This preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Bounded Seed-AGI Eric Nivel 1 , Kristinn R. Th´orisson 1 , 3 , Bas R. Steunebrink 2 , Haris Dindo 4 , Giovanni Pezzulo 5 , Manuel Rodr´ ıguez 6 , Carlos Hern´andez 6 , Dimitri Ognibene 5 , J¨urgen Schmidhuber 2 , Ricardo Sanz 6 , Helgi P. Helgason 3 , and Antonio Chella 4 1 Icelandic Institute for Intelligent Machines, IIIM 2 The Swiss AI Lab IDSIA, USI & SUPSI 3 Reykjavik University, CADIA 4 Universit`a degli studi di Palermo, DINFO 5 Consiglio Nazionale delle Ricerche, ISTC 6 Universidad Polit´ecnica de Madrid, ASLAB Abstract. Four principal features of autonomous control systems are left both unad- dressed and unaddressable by present-day engineering methodologies: (1) The ability to operate effectively in environments that are only partially known beforehand at de- sign 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 unforeseen changes in the environment; (3) The ability to operate effectively in environments 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 impede 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 under- specified circumstances, in a goal-directed way, on the job, by modeling itself and its environment as experience accumulates. The work provides an architectural blueprint for constructing systems with high levels of operational autonomy in underspecified circumstances, 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 autonomously sustained after the machine leaves the lab, within the boundaries imposed by its de- signers. A prototype system named AERA has been implemented and demonstrated to learn a complex real-world task—real-time multimodal dialogue with humans—by on-line observation. Our work presents solutions to several challenges that must be solved for achieving artificial general intelligence. 1 Introduction Our objective is to design control architectures for autonomous systems meant ultimately to control machinery (like for example robots, power grids, cars, plants, etc.). All physical systems have limited resources, and the ones we intend to build are no exception: they have limited computing power, limited memory, and limited time to fulfill their mission. All physical systems also have limited knowledge about their environment and the tasks they have to perform for accomplishing their mission. Wang [3] merged these two assumptions
Image of page 1

Info icon This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

What students are saying

  • Left Quote Icon

    As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

    Student Picture

    Kiran Temple University Fox School of Business ‘17, Course Hero Intern

  • Left Quote Icon

    I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

    Student Picture

    Dana University of Pennsylvania ‘17, Course Hero Intern

  • Left Quote Icon

    The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

    Student Picture

    Jill Tulane University ‘16, Course Hero Intern