Deliberation and voluntary action in 'conscious' software agents

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&...

Modelling real persons or virtual agents motivations, personality and emotions is a key feature of many useroriented applications. Most of the previous work has defined rich cognitive models of motivations, personality and emotions, but have relied on some kind of reactive scheme of problem solving and execution. Instead, this work proposes a deliberative emotional model for virtual agents based in their basic needs, preferences and personality traits. More specifically, we advocate the integration of these comprehensive agents models within deliberative automated planning techniques, so that plans to be executed by agents to achieve their goals already incorporate reasoning at the emotional level.

Affective interactions, 2000

2000

Here we will briefly describe action selection and language generation mechanisms in two'life-like'software agents, CMattie and IDA, and discuss issues that bear on the topics of architectures for behavior control, interdependencies between emotions and goal-based behaviors, and coordination of scripted and improvised behaviors. These agents are life-like in the sense of interacting with humans via email in natural language. They are'conscious' only in the sense of implementing a psychological theory of consciousness [3, 4].

Lecture Notes in Computer Science, 2014

Software agents are often seen as "intelligent, autonomous software components." Interestingly, the question of efficient implementation of "intelligence" remains open. In this paper we discuss, in some details, the process of implementing software agents with "brains." In the context of an agent system supporting decisions of glider pilots, we consider native implementation of "intelligent" behaviors, rule based engines, and semantic data processing. Based on the analysis of the stateof-the-art in these areas, we present a novel approach combining rule based engines, semantic data processing and software agents. V Rule-based Engine Developer(s) Stable release License Website Drools Red Hat 6.0.0 / 2013-12-20 ASL 2 http://drools.jboss.org/ DTRules Andreas Viklund 4.3 / 2011-07-05 ASL http://dtrules.com/ Hammurapi Rules Hammurapi Group 5.7.0 / 2009-01-11 LGPL http://www.hammurapi.biz/ Jena rule-based reasoner Apache Software Foundation 2.11.

2001

Abstract We propose the use of autonomous software agents as cognitive models that generate testable hypotheses about human cognition. While such agents are typically produced to automate practical human tasks, they can be designed within the constraints of a psychological theory. As an example we describe an agent designed within global workspace theory that accommodates several other theories as well.

IEEE Conference on Self Adaptive and Self Organizing Systems, 2010

The logical road to human-level AI is a dead end. Human-level AI requires compassionate intelligence to guide interaction and build applications and operating systems of the future. The cognition of such an agent includes Metacognition: thinking about thinking, thinking about feeling, and thinking about others' thoughts and feelings. We summarize the core meta-architectures and meta-processes of EM-2, a meta-cognitive agent that uses affective inference and an irrational TMS, the I-TMS, to resolve the turf war between thoughts and feelings based on agent personality and social and cultural knowledge as well as logic. The work is inspired as much by a human mind training process from India as it is by the 17th century commonsense philosopher David Hume. Although separated by more than 2000 years they both present a philosophy of mind where emotion is the antecedent to logical thought.

Journal of Artificial General Intelligence

Natural selection has imbued biological agents with motivations moving them to act for survival and reproduction, as well as to learn so as to support both. Artificial agents also require motivations to act in a goal-directed manner and to learn appropriately into various memories. Here we present a biologically inspired motivation system, based on feelings (including emotions) integrated within the LIDA cognitive architecture at a fundamental level. This motivational system, operating within LIDA’s cognitive cycle, provides a repertoire of motivational capacities operating over a range of time scales of increasing complexity. These include alarms, appraisal mechanisms, appetence and aversion, and deliberation and planning.

2014

ConAg is a reusable framework, written in Java, for creating \conscious " software agents. The system provides an application skeleton that can be customized by developers. Its particular focus is on these agents ' \consciousness " mechanism. A \conscious " software agent is a cognitive agent that integrates numerous articial intelligence mechanisms to implement the global workspace theory, a psychological theory of mind. This article gives an overview of \conscious " software agents and it describes the architectural style of \conscious " software agents, from which ConAg is constructed.

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