An action selection mechanism for'conscious' software agents

2003

Abstract ConAg is a reusable framework, written in Java, for creating “conscious” software agents. Its particular focus is on these agents'“consciousness” mechanism. A “conscious” software agent is an cognitive agent that integrates numerous artificial intelligence mechanisms to implement Bernard Baars' global workspace theory, a psychological theory of mind. This article gives overviews of “conscious” software agents and the need for a software reuse strategy for these agents' development.

Consciousness and Cognition, 1999

Affective interactions, 2000

Evidence of the role of emotions in the action selection processes of environmentally situated agents continues to mount. This is no less true for autonomous software agents. Here we are concerned with such software agents that model a psychological theory of consciousness, global workspace theory. We briefly describe the architecture of two such agents, CMattie and IDA, and the role emotions play in each. Both agents communicate with humans in natural language, the first about seminars and the like, the second about job possibilities. IDA must also deliberate on various scenarios and negotiate with humans. In CMattie emotions occur in response to incoming stimuli from the environment and affect behavior indirectly by strengthening or weakening drives. In IDA the emotions are integrated with the “consciousness” mechanism, and bidirectionally connected with all the major parts of the architecture. Thus, emotions will affect, and be affected by, essentially all of the agent’s disparat...

1993 Computer Architectures for Machine Perception, 1993

In contrast to “conscious”, reasoned behaviors, we consider behaviors that are automatic and unreasoned to be “unconscious”. The latter are commonly found in behavior-based AI models [BroSO, Maego]. We are developing an architecture that models agents with both “conscious” and “unconscious” behaviors. Furthermore, we are interested in modeling agents that learn behaviors from their successful interactions with the world. We

Here we describe mechanisms for a half-dozen or so different types of learning to be implemented in “conscious” software agents, and speculate briefly on their implications for human learning and development. In particular, we're concerned with conceptual learning and behavioral learning in two “conscious” software agents, namely, CMattie and IDA. We offer computational mechanisms for such learning.

Proceedings of The …, 1998

This paper describes the\ conscious" learning mechanism of an adaptive software agent, Conscious Mattie (CMattie). This conscious software agent takes the role of a departmental seminar organizer. The agent gathers seminar information via email from humans, composes an announcement of the next week's seminars, and mails it to members of a mailing list which she maintains. Through further interaction with seminar organizers, CMattie learns to handle new variations of seminars, such as colloquia. In this paper, the ...

2007

Evidence of the role of emotions in the action selection processes of environmentally situated agents continues to mount. This is no less true for autonomous software agents. Here we are concerned with such software agents that model a psychological theory of consciousness, global workspace theory. We briefly describe the architecture of two such agents, CMattie and IDA, and the role emotions play in each. Both agents communicate with humans in natural language, the first about seminars and the like, the second about job possibilities. IDA must also deliberate on various scenarios and negotiate with humans. In CMattie emotions occur in response to incoming stimuli from the environment and affect behavior indirectly by strengthening or weakening drives. In IDA the emotions are integrated with the "consciousness" mechanism, and bidirectionally connected with all the major parts of the architecture. Thus, emotions will affect, and be affected by, essentially all of the agent&...

2001

Abstract Robust autonomy on the part of software agents requires, at least in part, the ability to deal intelligently with novel and unexpected situations. According to global workspace theory, dealing with such situations is one of the primary functions of consciousness in humans. Below we briefly describe two software agents that implement this psychological theory, and discuss their resulting potential for robust autonomy.

1996

We present a general architecture for autonomous artificial agents that allows them to cope with the occurrence of internal and external stimuli simultaneously to their ongoing cognitive activities. This new architecture develops general proposals by Simon [1967] and Sloman [1987; 1995] particularized to the model described in [Botelho and Coelho 1995]. We relate the dispute between the primacy of affect and the primacy of cognition to the proposed architecture. Within the mentioned architecture we describe a new mechanism based on emotion and attribution, for controlling attention shift. Automatic as opposed to thoughtful and deliberate decision is a fundamental asset of our approach. Such automaticity is only possible because it draws on properties of the SALT model of memory [Botelho and Coelho 1995]. We relate our proposal to previous work on attention shift [Beaudoin and Sloman 1993], dynamic context-dependent change [Maes 1989] and commitment policies [Pollack and Ringuette 1990] and [Kinny and Georgeff 1991], and show how these former mechanisms may be defined within the proposed architecture. 1-Introduction Attention shift refers to what happens when some agent stops attending to its current thinking and attends to some external or internal event or object.