3 Types Flashcards
7 agent types
- Collaborative Agents
- Interface Agents
- Mobile Agents
- Internet / Information agents
- Reactive agents
- Hybrid agents
- Heterogeneous systems
collaborative agents
Collaborative agents are usually deliberative agents (e.g. based on the BDI model), with some reasoning capabilities. They normally have very limited learning capabilities and negotiate with their peers to reach mutually acceptable agreements during cooperative problem solving.
-> solve problems that are too large for a single centralised agent or that are inherently distributed
collaborative agents
applications
- Provide solutions to physically distributed problems
air-traffic control, management of a team of robots - Provide solutions to problems with distributed data sources
different offices of a multi-national business - Provide solutions that need distributed expertise
health care provision (family doctors, nurses, specialists, laboratory analysis…
interface agents
Autonomy and learning in order to perform tasks for their owners. Support and provide proactive assistance to a human. Anticipate user needs, make suggestions, provide advide without explicit user request
- limited cooperation with other agents
- limited reasoning and planning capabilities
-> personal assistant
- automation of routine activities
- learn and adapt
interface agents
applications
Personal assistant Mail management Scheduling meetings Internet browsing News filtering agent Buying/selling on behalf of the user Negotiate a meeting time with other agents
information agents
Information agents = Internet agents
Main task: proactive acquisition, mediation and maintenance of relevant information for a user/other agents, manage the access to multiple, heterogeneous and geographically distributed information sources.
- information retrieval
- information synthesis and presentation
- learn and adapt to user preferences
information agents
applications
web search engines (crawl, process, compute popularity, build index, store information)
information agents (learn and adapt to user preferences)
heterogeneous systems
Homogeneous system: all agents belong to the same type. Agentification of existing applications.
Architectures:
- flat (any agent can talk to any)
- federated system (special agents manage the connections)