software agent -design issues-
DESCRIPTION
Software Agent -design issues-. Outline. Agent review Approaches to building applications Agent & interagent programming tips Incremental system development & evaluation Summary. What is an Agent?. Voyager, Aglets, Odyssey. Mobile Agents Programs that move among computer hosts - PowerPoint PPT PresentationTRANSCRIPT
Software Agent-design issues-
Outline
• Agent review
• Approaches to building applications
• Agent & interagent programming tips
• Incremental system development & evaluation
• Summary
2/20
What is an Agent?
Mobile AgentsPrograms that move among computer hosts
Autonomous Agents Based on planning technologies
Learning AgentsUser preferences, collaborative filtering,...
Animated Interface AgentsAvatars, chatbots, ...
Simulation-based EntitiesData/Info finding, filtering and mergingCooperative Agents
Cooperation among distributed heterogeneous programmatic components
Voyager, Aglets, Odyssey
Robots, Softbots, BDI
Microsoft Agent, Julia
ModSAF, RoboCup
OAA, KQML, FIPA
FireFly, MIT Media Lab
SIMS, InfoSleuth, IR
3/20
Approaches to Building Applications
MonolithicApplications
Object-Oriented Applications
Distributed ObjectApplications
OAAApplications
Dynamic addition
Objective
Suitable for Internet environmentVirtual community of dynamic services
Adaptable to changing, evolving network resources
Flexible interactions among components
4/20
Approaches to Distributed Computing
• Mobile objects
• Blackboard architectures
• Agent communication languages (ACL)
• Publish & subscribe brokers
5/20
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
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– Polling tuple(abc,1,2,3)
7/20
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– Simple filtering, unitary messages
Broker
8/20
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
ANS, Service BrokerAsk
Reply
9/20
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
Agent & Interagent Programming Tips
• Choosing an agent Interface
• Information sharing strategies
• Domain-specific vs. domain-independent agents
• Adding speech & NL to interfaces
11/20
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
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 in-stall 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
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
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
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
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
Subject Screen vs. Wizard Screen
18/20
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 en-hancement
• Improvements from data analysis quantifiable
• General-purpose approach
19/20
Hybrid WOZ: Implementation
• System logging and playback “for free” using OAA collaboration facili-ties
• “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
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
• Next class ( 인지구조 )– 1. Human symbol manipulation within an integrated cognitive architecture, Cogni-
tive Science, 2005. ( 최봉환 )– 2. The importance of cognitive architectures: An analysis based on CLARION,
Journal of Experimental and Theoretical Artificial Intelligence, 2007. ( 이영설 )– 3. A Gentle Introduction to Soar: 2006 update, 2006. ( 김용준 )
21/20