14
Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science [email protected]

Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Embed Size (px)

DESCRIPTION

Can we make it real? When we have solved the ”AI problem”... But we don’t need to A computer can play a fair game of chess Agents may (should) address specific tasks

Citation preview

Page 1: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Software Agents &Agent-Based Systems

Sverker JansonIntelligent Systems LaboratorySwedish Institute of Computer [email protected]

Page 2: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

A somewhat trite vision...

Intelligent agents...• understand what we mean• find and use relevant

information• automate routine tasks• adapt to our needs and

desires• cooperate with other

assistants• et c, et c

Cf. Knowledge Navigator ’87, featuring Phil

Page 3: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Can we make it real?

• When we have solved the ”AI problem” ...

• But we don’t need to• A computer can play

a fair game of chess• Agents may (should)

address specific tasks

Page 4: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Common characteristics...

Agents are...• situated• autonomous• reactive• pro-active• social• rational• et c, et c

Cf. Jennings, Sycara, Wooldridge, A Roadmap of Agent Research and Development, JAAMAS, 1998

Page 5: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Commonmetaphore?

Agent-based systems

Systems & informationintegration Multiagent

systems

ResourcemarketsInternetcommerceRecommendersystems

Software agents

Agents

Assistant agents

Believable agents

Simulated agents

Economics

People...

Sociology

Robots

Mobile agents

Artificial life

Page 6: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Personal assistant agents

• Reducing work and information overload

• Examples– Apple’s Knowledge

Navigator– MIT Media Lab

(various) – Microsoft Paper Clip– Office of Naval

Research Tactical Picture Agent

Page 7: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Mobile agents

• Moving running software between computers

• Purpose– overcome network latency

(e.g. interact in real time)– use located resources

(e.g. computing power, storage, special hardware)

– see e.g. Seven Good Reasons for Mobile Agents by Lange and Oshima, CACM 3(42)

• Problems– Security, trust,

performance

Page 8: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Mobile agents, unique selling point…

Page 9: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Agent-based systems

Page 10: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

How communicate?

• Sharing information & bridging data models

• High level speech act based protocols– KQML / FIPA ACL– Cf. SOAP

• Expressive logic based content formats– KIF / FIPA SL– Cf. semantic web

• Systems and information integration

TELL p(a)

Page 11: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

How coordinate?

• Coordinating different interests and goals

• Agent: locus of self-interest

• Market based interaction– Contract net– Combinatorial markets

• Combination with organization– Coalition formation

• Multiagent systems, e.g. automated markets

Page 12: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Objects vs agents

• Objects– state– methods– control– method invocation

• Agents– goals– knowledge– planning– negotiation

Page 13: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Agents address software complexity• Complex functionality?

– “mechanistic” explanation too complex?

– replace direct manipulation with dialogue

– from understanding to trust

– Cf. assistant agents

• Complex interrelationships?– let components be

“selfish”– interaction through

negotiation– global properties by

mechanism design– Cf. agent-based systems

Page 14: Software Agents & Agent-Based Systems Sverker Janson Intelligent Systems Laboratory Swedish Institute of Computer Science

Whose agent?