Extending Agent Capabilities: Tools vs. Agents

Acay, Daghan L.; Tidhar, Gil; Sonenberg, Liz

doi:10.1109/wiiat.2008.247

Cited by 7 publications

(6 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The agent has beliefs, goals and capabilities. This is in accordance with the theoretical model of Acay et al [8]. The agent's plans have been simplified to specify just the agent's capabilities.…”

Section: A Model For Artifact Capability-learning Agentmentioning

confidence: 63%

“…Although our model provides a representation for an artifact, further experiments need to be conducted involving the use of artifacts with other artifacts. Acay et al's [8] theoretical model for external capabilities supports agents gaining capabilities from tools or other agents. The tool capability explored in this paper could be extended to include capabilities of other agents.…”

Section: Discussionmentioning

confidence: 99%

“…To keep the artifact model simple, it is assumed that the artifact the agent is attempting to use can be used only once, and will depreciate once the agent successfully uses it. Researchers have debated on whether capability involves both ability and opportunity [8]. In this paper, an agent has capability for an artifact if it knows one way to use the artifact and has the opportunity to use the artifact.…”

Section: A Artifact Modelmentioning

confidence: 99%

“…The agent's intentions or adopted goals are used to generate plans or actions that the agent will perform. Logical foundations of the BDI theory have been extended to include internal and external capabilities [8]. In their logical representation, an agent's capabilities reside within its intentions and specify either plans that the agent can accomplish on its own (internal), or plans that the agent can accomplish with the help of a tool or another agent (external).…”

Section: Introductionmentioning

confidence: 99%

“…In this paper we implement an extended version of the theoretical model for tool capability provided by Acay et al [8], that accommodates evolution and learning of artifact capabilities through exploratory methods. External capabilities with respect to other agents are considered to be beyond the scope of the paper.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Evolution of artifact capabilities

Mokom

Kobti

2011

2011 IEEE Congress of Evolutionary Computation (CEC)

View full text Add to dashboard Cite

The subject of artifact or tool use is considered in many fields to be a vital area of research in the study of general human competence. Recently in artificial intelligence, formalizations of the mental attitudes of intentional agents have been extended to include agent capabilities with respect to artifacts or tools. We consider understanding how these individual capabilities are learned and how they evolve as important steps towards formally defining, representing and implementing complex group capabilities. In this paper, a theoretical model for artifact capability is extended to incorporate evolution and learning through exploratory methods. A representation of artifacts and the cognition of a rational agent that can learn artifact use are provided. Supervised learning is assumed and combined with historical knowledge and genetic algorithms to provide an implementation of a multi-agent simulation. The simulation is built to support an agent with the ability to learn an artifact capability through observations of its own behavior, as well as through observations of other agents in a social environment. Results obtained from the simple yet practical approach, show that learned use of artifacts outperforms random use and rational agents can learn artifact use more efficiently as a social species than on their own.

show abstract

Section: A Model For Artifact Capability-learning Agentmentioning

confidence: 63%

Section: Discussionmentioning

confidence: 99%

Section: A Artifact Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Evolution of artifact capabilities

Mokom

Kobti

2011

2011 IEEE Congress of Evolutionary Computation (CEC)

View full text Add to dashboard Cite

show abstract

Adaptive Coordination in Distributed and Dynamic Agent Organizations

Keogh

Sonenberg

2012

Coordination, Organizations, Institutions, and Norms in Agent System VII

Self Cite

View full text Add to dashboard Cite

We elaborate the rationale and design of OJAzzIC (Organizations Joining Adaptively with Improvised Coordination), a model for agents in (Jazzy) Organizations that need to engage in dynamic adaptation to respond to a dynamic situation. OJAzzIC provides an adaptive data structure and framework for creation of multiple instances of organizations within a distributed system, with knowledge sharing across organizational boundaries achieved through overlapping instances.

show abstract