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 reassess and redefine 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 gracefullyhow 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 underspecified 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 designers. 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.

Abstract-In the domain of intelligent systems the management of system resources is typically called "attention". Attention mechanisms exist because even environments of moderate complexity are a source of vastly more information than available cognitive resources of any known intelligence can handle. Cognitive resource management has not been of much concern in artificial intelligence (AI) work that builds relatively simple systems for particular targeted problems. For systems capable of a wide range of actions in complex environments, explicit management of time and cognitive resources is not only useful, it is a necessity. We have designed a general attention mechanism for intelligent systems. While a full implementation remains to be realized, the architectural principles on which our work rests have already been implemented. Here we examine some prior work that we find relevant to engineered systems, describe our design, and how it derives from constructivist AI principles.

Abstract. Many existing AGI architectures are based on the assumption of infinite computational resources, as researchers ignore the fact that real-world tasks have time limits, and managing these is a key part of the role of intelligence. In the domain of intelligent systems the management of system resources is typically called "attention". Attention mechanisms are necessary because all moderately complex environments are likely to be the source of vastly more information than could be processed in realtime by an intelligence's available cognitive resources. Even if sufficient resources were available, attention could help make better use of them. We argue that attentional mechanisms are not only nice to have, for AGI architectures they are an absolute necessity. We examine ideas and concepts from cognitive psychology for creating intelligent resource management mechanisms and how these can be applied to engineered systems. We present a design for a general attention mechanism intended for implementation in AGI architectures.

No abstract

Abstract:Much of present AI research is based on the assumption of computational systems with infinite resources, an assumption that is either explicitly stated or implicit in the work as researchers ignore the fact that most real-world tasks must be finished within certain time limits, and it is the role of intelligence to effectively deal with such limitations. Expecting AI systems to give equal treatment to every piece of data they encounter is not appropriate in most real-world cases; available resources are likely to be insufficient for keeping up with available data in even moderately complex environments. Even if sufficient resources are available, they might possibly be put to better use than blindly applying them to every possible piece of data. Finding inspiration for more intelligent resource management schemes is not hard, we need to look no further than ourselves. This paper explores what human attention has to offer in terms of ideas and concepts for implementing intelligent resource management and how the resulting principles can be extended to levels beyond human attention. We also discuss some ideas for the principles behind attention mechanisms for artificial (general) intelligences.