Cognitive Architecture Requirements for Achieving AGI

In this paper, we examine the motivations for research on cognitive architectures and review some candidates that have been explored in the literature. After this, we consider the capabilities that a cognitive architecture should support, some properties that it should exhibit related to representation, organization, performance, and learning, and some criteria for evaluating such architectures at the systems level. In closing, we discuss some open issues that should drive future research in this important area.

Artificial Intelligence, 1987

The ultimate goal of work in cognitive architecture is to provide the foundation for a system capable of general intelligent behavior. That is, the goal is to provide the underlying structure that would enable a system to perform the full range of cognitive tasks, employ the full range of problem-solving methods and representations appropriate for the tasks, and learn about all aspects of the tasks and its performance on them. In this article we present Soar, an implemented proposal for such an architecture. We describe its organizational principles, the system as currently implemented, and demonstrations of its capabilities.

… of the 2008 conference on Artificial …, 2008

Cognitive architectures play a vital role in providing blueprints for building future intelligent systems supporting a broad range of capabilities similar to those of humans. How useful are existing architectures for creating artificial general intelligence? A critical survey of the state of the art in cognitive architectures is presented providing a useful insight into the possible frameworks for general intelligence. Grand challenges and an outline of the most promising future directions are described. : "W. Duch".

Cognitive Systems Research, 2009

In this paper, we examine the motivations for research on cognitive architectures and review some candidates that have been explored in the literature. After this, we consider the capabilities that a cognitive architecture should support, some properties that it should exhibit related to representation, organization, performance, and learning, and some criteria for evaluating such architectures at the systems level. In

Atlantis Thinking Machines, 2012

By exploring the relationships between different AGI architectures, one can work toward a holistic cognitive model of human-level intelligence. In this vein, here an integrative architecture diagram for human-like general intelligence is proposed, via merging of lightly modified version of prior diagrams including Aaron Sloman's high-level cognitive model, Stan Franklin and the LIDA group's model of working memory and the cognitive cycle, Joscha Bach and Dietrich Dorner's Psi model of motivated action and cognition, James Albus's three-hierarchy intelligent robotics model, and the author's prior work on cognitive synergy in deliberative thought and metacognition, along with ideas from deep learning and computational linguistics. The purpose is not to propose an actual merger of the various AGI systems considered, but rather to highlight the points of compatibility between the different approaches, as well as the differences of both focus and substance. The result is perhaps the most comprehensive architecture diagram of human-cognition yet produced, tying together all key aspects of human intelligence in a coherent way that is not tightly bound to any particular cognitive or AGI theory. Finally, the question of the dynamics associated with the architecture is considered, including the potential that human-level intelligence requires cognitive synergy between these various components is considered; and the possibility of a "trickiness" property causing the intelligence of the overall system to be badly suboptimal if any of the components are missing or insufficiently cooperative. One idea emerging from these dynamic consideration is that implementing the whole integrative architecture diagram may be necessary for achieving anywhere near human-level, human-like general intelligence.

arXiv (Cornell University), 2024

The article identified 42 cognitive architectures for creating general artificial intelligence (AGI) and proposed a set of interrelated functional blocks that an agent approaching AGI in its capabilities should possess. Since the required set of blocks is not found in any of the existing architectures, the article proposes a new cognitive architecture for intelligent systems approaching AGI in their capabilities. As one of the key solutions within the framework of the architecture, a universal method of knowledge representation is proposed, which allows combining various non-formalized, partially and fully formalized methods of knowledge representation in a single knowledge base, such as texts in natural languages, images, audio and video recordings, graphs, algorithms, databases, neural networks, knowledge graphs, ontologies, frames, essence-property-relation models, production systems, predicate calculus models, conceptual models, and others. To combine and structure various fragments of knowledge, archigraph models are used, constructed as a development of annotated metagraphs. As components, the cognitive architecture being developed includes machine consciousness, machine subconsciousness, blocks of interaction with the external environment, a goal management block, an emotional control system, a block of social interaction, a block of reflection, an ethics block and a worldview block, a learning block, a monitoring block, blocks of statement and solving problems, self-organization and meta learning block.

2017

The term " Cognitive Architectures " indicates both abstract models of cognition, in natural and artificial agents, and the software instantiations of such models which are then employed in the field of Artificial Intelligence (AI). The main role of Cognitive Architectures in AI is that one of enabling the realization of artificial systems able to exhibit intelligent behavior in a general setting through a detailed analogy with the constitutive and developmental functioning and mechanisms underlying human cognition. We provide a brief overview of the status quo and of the potential role that Cognitive Architectures may serve in the fields of Computational Cognitive Science and Artificial Intelligence (AI) research.

submission to Artificial …, 2005

The Engine for Composable Logical Agents with Intuitive Reorganization (ECLAIR) is a cognitive agent architecture that allows an agent to quickly adapt its behavior to new environments. ECLAIR addresses two problems in agent learning: generalizing the process of adaptation and detecting when adaptation is required. ECLAIR incorporates the main mechanisms from Piaget's Cognitive-Stage Theory of Development [10], and it uses concepts from Damasio's Somatic Marker Hypothesis [4] for discovery of what should be learned. ECLAIR has modules for stimuli, awareness, plan behavior, reflex behavior, control/decision making, and adaptivity. ECLAIR agents take a hybrid approach to action. In normal situations they act logically, using plans, when there is a known strategy to accomplish a task. However, when quick reaction is needed, motivation for action is intuitive or emotional. The agent fires reflexes triggered by changes in the agent's perception of personal well being. Adaptive learning extends both cognitive and emotional behavior in our architecture. We demonstrated the cognitive architecture and reflexive adaptation using a simulation for network-centric warfare logistics. 1. COGNITIVE ARCHITECTURES Researchers have strived to develop cognitive architectures since the 1980s. The main premise of these types of architectures is to emulate the human, how a person makes decisions, represents information, and learns. The two most widely known cognitive architectures with a psychological basis are SOAR [9] and ACT-R [1]. Both are hypotheses for answering Newell's concept of a United Theory of Cognition [12]. Newell saw that in a person, there are many interacting components that must be integrated into a single comprehensive system, and believed that the single system is the source of all behavior. Thus, the goal of a cognitive architecture is to have one system that gives purpose to the many components that make up a thinking person. ACT-R is a cognitive architecture designed as an integration of components discovered in psychology research. This model is primarily meant to accurately simulate human behavior. Given a specific cognitive theory, ACT-R can be used to model the components of the theory. Once the model has been created, experiments can be made that get results very similar to human experimental results. In addition, the model can be used to extend previous theories by creating a novel experiment for the model. ACT-R also has a set of modules that represent different functional aspects of the brain. The modules interact when each module exposes part of its activity into a public buffer. The 3. ECLAIR ARCHITECTURE The main elements of ECLAIR architecture (Fig.

Cognitive Systems Research, 2018

In this paper we identify and characterize an analysis of two problematic aspects affecting the representational level of cognitive architectures (CAs), namely: the limited size and the homogeneous typology of the encoded and processed knowledge. We argue that such aspects may constitute not only a technological problem that, in our opinion, should be addressed in order to build artificial agents able to exhibit intelligent behaviours in general scenarios, but also an epistemological one, since they limit the plausibility of the comparison of the CAs' knowledge representation and processing mechanisms with those executed by humans in their everyday activities. In the final part of the paper further directions of research will be explored, trying to address current limitations and future challenges.

this paper presents a review of "How AI, cognitive science and DM are combined to develop intelligent agents", and how the paradigm first shifted from AI to Data mining and then towards combination of data mining and artificial intelligence. The paper will also provide a state-of-the-art account of the cognitive architectures. It also gives a detailed comparative study of all the architectures discussed in the paper. All the survey of data mining and cognitive architecture is done w.r.t Multi agent systems. Therefore, paper will also provide a bird eye view of MAS/ ABMS.