Bounded Recursive Self-Improvement

12/24/2013
by   E. Nivel, et al.
0

We have designed 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 experience accumulates. Based on principles of autocatalysis, endogeny, and reflectivity, the work provides an architectural blueprint for constructing systems with high levels of operational autonomy in underspecified circumstances, starting from a small seed. Through value-driven dynamic priority scheduling controlling the parallel execution of a vast number of reasoning threads, the system achieves recursive self-improvement after it leaves the lab, within the boundaries imposed by its designers. A prototype system 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.

READ FULL TEXT

page 1

page 23

page 52

research
11/12/2017

Self-Regulating Artificial General Intelligence

Here we examine the paperclip apocalypse concern for artificial general ...
research
08/25/2009

Predictability of Fixed-Job Priority Schedulers on Heterogeneous Multiprocessor Real-Time Systems

The multiprocessor Fixed-Job Priority (FJP) scheduling of real-time syst...
research
05/07/2017

A Reconnaissance Attack Mechanism for Fixed-Priority Real-Time Systems

In real-time embedded systems (RTS), failures due to security breaches c...
research
01/16/2020

On Schedulability Analysis of EDF Scheduling by Considering Suspension as Blocking

During the execution of a job, it may suspend itself, i.e., its computat...
research
05/17/2018

A Formulation of Recursive Self-Improvement and Its Possible Efficiency

Recursive self-improving (RSI) systems have been dreamed of since the ea...
research
09/15/2021

Recursive Hierarchical Projection for Whole-Body Control with Task Priority Transition

Redundant robots are desired to execute multitasks with different priori...
research
10/07/2022

GoalsEye: Learning High Speed Precision Table Tennis on a Physical Robot

Learning goal conditioned control in the real world is a challenging ope...

Please sign up or login with your details

Forgot password? Click here to reset