7
Download as PPT, PDF•0 likes•321 views
This document discusses issues in designing software agent applications. It covers agent types, approaches to building distributed applications using agents, agent communication methods, and tips for agent and interagent programming. It also discusses incremental development and evaluation of agent systems using a hybrid wizard of oz experiment approach.
![Information Sharing Strategies (1)
• Example: Phone dialer agent
• 1. Query
– When an agent wants to know the status of the
phone, it asks the Facilitator who asks the phone
agent
– pa: oaa_Declare(status(phone, S),[])
– ?a: oaa_Solve(status(phone, S), [])
• 2. Post (Blackboard)
– The phone agent writes its status to the Facilitator;
agents can query the facilitator for status, and
install a trigger which proactively monitors changes
to status
– pa: oaa_AddData(status(phone, busy), [])
– ia: oaa_Solve(status(phone, S), []),
oaa_AddTrigger(data, status(phone,S), notify(Me,
phone(S)), [on(change)])
13/20
13/20](https://image.slidesharecdn.com/7-121229011931-phpapp02/85/7-13-320.jpg)
![Information Sharing Strategies (2)
• 3. Inform
– Broadcast time-critical events to interested parties
– ia: oaa_Declare(msg(phone, Msg), [])
– pa: oaa_Solve(msg(phone, ringing, []), [inform])
14/20
14/20](https://image.slidesharecdn.com/7-121229011931-phpapp02/85/7-14-320.jpg)
7
- 2. Outline • Agent review • Approaches to building applications • Agent & interagent programming tips • Incremental system development & evaluation • Summary 2/20
- 3. What is an Agent? Voyager, Aglets, Odyssey Mobile Agents Programs that move among computer hosts Robots, Softbots, Autonomous Agents BDI Based on planning technologies FireFly, MIT Media Learning Agents Lab User preferences, collaborative filtering,... Microsoft Agent, Julia Animated Interface Agents Avatars, chatbots, ... ModSAF, RoboCup Simulation-based Entities SIMS, InfoSleuth, IR Data/Info finding, filtering and merging OAA, KQML, FIPA Cooperative Agents Cooperation among distributed heterogeneous programmatic components 3/20
- 4. Approaches to Building Applications Monolithic Object-Oriented Distributed Object Applications Applications Applications Objective Suitable for Internet environment Virtual community of dynamic services Adaptable to changing, evolving Dynamic addition network resources Flexible interactions among OAA components Applications 4/20
- 5. Approaches to Distributed Computing • Mobile objects • Blackboard architectures • Agent communication languages (ACL) • Publish & subscribe brokers 5/20
- 6. Mobile Objects (Agents) • Objects move under their own power (e.g., Voyager, Aglets) • Advantages – Network bandwidth for certain classes of problems – Parallelism - many objects can be spawned • Disadvantages – Programmatically specify where to go and what to do, through a known interface – Little automated support for inter-object cooperation – Programming language specific (non-heterogeneous) 6/20
- 7. Blackboard Architectures • Knowledge Sources read and write tuples from a common information space (e.g. LINDA, FLiPSiDE) • Advantages – Eliminates explicitly programmed interactions among participants • Disadvantages – KS cannot coordinate interactions tuple(abc,1,2,3) – Polling 7/20
- 8. Publish & Subscribe Brokers • Clients register interest, broker routes/filters msgs • Examples: Talarian SmartSockets, Active Software’s ActiveWeb, ACL Brokers • Advantages – Destination process(es) not explicitly encoded – No polling • Disadvantages Broker – Simple filtering, unitary messages 8/20
- 9. Agent Communication Languages • Communication message types based on speech acts (e.g., ask, tell, deny) + conversational policies • Examples: FIPA ACL, KQML • Advantages – Rich interaction model, peer-to-peer based – Standardized message types, content-agnostic • Disadvantages – Conformance to specs not universal – Explicitly coded interactions among participants Ask ANS, Service Broker Reply 9/20
- 10. Comparison of Distributed Approaches Distributed Dist. Objects, Mobile Agents, ACL, Blackboards, Pub/Sub Heterogeneous languages Distributed Objects, ACL, Blackboards Non-coded interactions Blackboards, Pub/Sub Parallel Services Blackboards Compound Expressions (Mobile Agents) Constraints No 10/20 10/20
- 11. Agent & Interagent Programming Tips • Choosing an agent Interface • Information sharing strategies • Domain-specific vs. domain-independent agents • Adding speech & NL to interfaces 11/20 11/20
- 12. Choosing an Agent Interface • Natural-language inspired interfaces – Imperative Verb, Direct Object, ParamList, (Result) – Parameter lists hold Adjs, Advs & Prepositions as well as extensible programmatic instruction • Classes tagged by type – inform(phone, ringing, Params) – send_message(MsgRef, Params) :- memberchk(by(fax), Params) • Succeed once with list vs. Multiple success – get(email, message_headers, +Params, -ListOfHeaders) – phone_number(Person, PhoneNum) 12/20 12/20
- 13. Information Sharing Strategies (1) • Example: Phone dialer agent • 1. Query – When an agent wants to know the status of the phone, it asks the Facilitator who asks the phone agent – pa: oaa_Declare(status(phone, S),[]) – ?a: oaa_Solve(status(phone, S), []) • 2. Post (Blackboard) – The phone agent writes its status to the Facilitator; agents can query the facilitator for status, and install a trigger which proactively monitors changes to status – pa: oaa_AddData(status(phone, busy), []) – ia: oaa_Solve(status(phone, S), []), oaa_AddTrigger(data, status(phone,S), notify(Me, phone(S)), [on(change)]) 13/20 13/20
- 14. Information Sharing Strategies (2) • 3. Inform – Broadcast time-critical events to interested parties – ia: oaa_Declare(msg(phone, Msg), []) – pa: oaa_Solve(msg(phone, ringing, []), [inform]) 14/20 14/20
- 15. Domain-specific vs. Domain-independent • Move domain-dependent code into separate agent • Employ hooks and parameters to allow domain-specific tailoring of functionality • Always ask: Domain-specific or domain independent? – Phone agent? – Office interface? – Notify agent? – Speech recognition? – Natural language? – Facilitator? 15/20 15/20
- 16. Adding Speech & NL • User Interface responsible for: – accepting user input, sending requests, displaying results – controlling interactions of speech and NL • Complex interpretation processed by external domain agent 16/20 16/20
- 17. Incremental System Development & Evaluation • Collaborative Multimodal Map application adapted for Wizard Of Oz (WOZ) experiment to elicit data about coordinated use of language and gesture 17/20 17/20
- 18. Subject Screen vs. Wizard Screen 18/20 18/20
- 19. Hybrid Wizard Of Oz Experiment • Naive user free to write, draw, or speak without constraints imposed by current technology • Wizard must respond quickly and accurately by using existing means, including pen and voice • Simultaneous evaluation of: – Experienced user manipulating real system – New user, providing data for future extensions • Bootstrap effect: continuous loop from data to theory, to system enhancement • Improvements from data analysis quantifiable • General-purpose approach 19/20 19/20
- 20. Hybrid WOZ: Implementation • System logging and playback “for free” using OAA collaboration facilities • “Subject mode”: functional interpretation (mostly) turned off • Addition of simple Wizard Feedback panel (separate agent) for text- to-speech messages (e.g., “Function not available.”) 20/20 20/20
- 21. Summary • Review of designing issues in software agents • Not good for every application, but good for: – integrating numerous components which need to cooperate, often across language boundaries – supporting media translation – distributed reference resolution – tasking through adaptable or multimodal user interfaces – human/agent collaborative systems & incremental dvpt – exploring direct manipulation/task delegation tradeoffs 21/20 21/20