1. AOSE Multi-Agent Interaction

2. Agents and Interaction Interaction forms the basis of an agents collaborative problem solving capabilities. –Agents are designed to operate in tandem with one another. –This includes sharing and requesting knowledge, negotiating services, coordinating activities, … Key to realisation of such activities is the implementation of an underlying communication mechanism. Two broad approaches to communication: –Shared space communication –Communication by message passing

3. Message Passing General Principle: –Messages sent directly receiver agent (1:1 communication). –Message transmission handled by a communication channel. –Message format based on an agreed communication language. –Interaction consists of several messages where the agents take their turns as sender and receiver. –This is called a dialog or a protocol. This model of message-passing is more traditional: –Modern message-oriented middleware supports factures such as: presence management, message persistence, security, multcast, publish/subscribe, …

4. Message Passing Advantages: –Well suited to internet scale applications. –Communication is directed to relevant agents (no information overload). –More Robust: So long as the communication channel is decentralised. Disadvantages: –Agent Discovery: new agents must register their existence. –Choosing an appropriate communication language. –Defining and enforcing protocols.

5. Foundations A core issue underlying the design of message-passing based communication is the format of the messages. –Our goal is to support agent interactions that exhibit the flexibility that is inherent within human conversation. As with many agent concepts, we look to philosophy in for inspiration… Speech Act Theory (Searle, 1969) is a pragmatic theory of language. –It attempts to account for how language is used by people every day to achieve their goals and intentions. –It achieves this by adopting a view of speech as action.

6. Austin’s Theory The origin of speech act theories are usually traced to the work of the philosopher John Austin. Austin noticed that some utterances are like ”physical actions” that appear to change the state of the world. e.g. –Declaring war –”I now pronounce you man and wife” Austin distinguished 3 different aspects of speech acts: –Locutionary act - act of making an utterance e.g. saying ”please make some tea” ’ –Illocutionary act – action performed in saying something e.g. he requested me to make some tea –Perlocution – effect of the act e.g. he got me to make tea

7. Searle’s Theory Searle built on Austins work and identified 5 types of illocutionary act (which he called speech acts): Speech Act TypeDescription and Example Representatives or Assertives Informing e.g. ”It is raining”. DirectivesSpeaker tries to make the hearer do something e.g. ”Please close the window” CommisivesCommits the speaker to future action e.g. ”I will close the window” ExpressivesSpeaker expresses a mental state e.g. ”Excuse me”, ”congratulations” DeclarativesEffect some changes e.g. ”I name this city Trondheim”

8. Speech ActPlease close the door The door is closedIs the door closed? Performativerequestinforminquire Contentthe door is closed Searle’s Theory He then determined that speech acts can be decomposed in to 2 core components: A performative verb e.g. Request, inform Propositional content e.g. ”the window is closed”

9. Agent Communication Languages An Agent Communication Language combines: –a data format for representing speech acts. –a (partial) model of the state of the speaker and hearer. –a formally specified set of speech act types (based on the above model). In theory: –speech act = performative verb + propositional content. In practice: –Contextual information, such as: who performed the speech act, and to whom it was directed. Minimal Practical Form: –request ( rem, bob ) “closed(door)”

10. Agent Communication Languages Human communication employs other contextual information: –The language spoken (format), social rules governing the conversation (protocol), the topic context / work meanings (ontology), … Typically, this information must also be provided in an ACL (although it is not always implemented in real world systems). Other information provided includes: –Encoding / Payload sizes / Routing Information –Conversation Management Tokens (reply with / in response to) The key value of ACL’s is that they define a clear syntax and semantics for agent communication.

11. AOSE FIPA Agent Interaction

12. Who is FIPA? The Foundation for Intelligent Physical Agents (FIPA) is a non- profit association. FIPA’s purpose is ”to promote the success of emerging agent-based applications, services and equipment.” FIPA operates through the open international collaboration of member organisations: –companies, universities and government organisations. FIPAs Standards Cover: –Agent Communication (FIPA ACL / Interaction Protocols) –AO-Application Infrastructures (Agent Platform, Agent Management, Message Transport Systems) –Agent UML

13. FIPA ACL: Structure Performative (communicative act) –20 performatives in FIPA ACL Housekeeping –e.g. Sender, Reply to, Reply-with, In-Reply-With Content –the actual content of the message Language –The language in which the content is written Ontology –The ontology in which the message needs to be interpreted.

14. FIPA ACL: Message Structure Envelope: –Comprises of a collection of parameters –Contains at least the mandatory to and sender parameters Message Body –The fully specified message in the chosen ACL syntax –Can be encoded (e.g. The FIPA Bit Efficient Encoding Mechanism). Transport-message: HTTP Sender: Transport-type: FIPA-HTTP Transport-address: http://www.agentfactory.com:4444/http://www.agentfactory.com:4444/ Transport-properties: none Receiver: Transport-type: FIPA-HTTP Transport-address: http://www.ibeca.org:4444/http://www.ibeca.org:4444/ Transport-properties: none Additional-attributes: none Payload (ACL message) Envelope

15. FIPA Transport management a platform provides each agent with a channel; a transfer protocol is used to transfer messages between channels; the transport service delivers messages within a platform or between platforms; ACL is the payload of the transport service and protocol; the envelope contains transport information.

16. FIPA ACL: Performative Semantics InformRequest Content statementaction Precondition Holds that the content is true. Intends that the recipient believe the content Does not already believe that the recipient is aware whether content is true or not Intends action content to be performed Believes recipient is capable of performing this action Does not believe that sender already intends to perform action

17. Performatives in FIPA

18. FIPA Agent Interaction Protocols Ongoing conversations between agents fall into typical patterns. –In such cases, certain message sequences are expected, and at any point in the conversation, other messages are expected to follow. These typical patterns of message exchange are called protocols. (query-if:sender A :receiver B :content some-act :protocol fipa-query-protocol )

19. FIPA Agent Interaction Protocols Basic FIPA Interaction Protocols: –Request Protocol –Query Protocol –Propose Protocol –Request When Protocol –Subscribe Protocol –Recruiting Protocol –Brokering Protocol Other FIPA Protocols: –English and Dutch Auctions, (Iterated) Contract Net

20. Example: Query Protocol The protocol states that: –IF an agent asks another agent if a proposition holds or not –THEN the participant must: –reply by informing the initiator of the answer, –refuse to answer, –fail to answer, or –fail to understand the question.

21. Example: Request Protocol Initiator requests that some activity / action be performed Participant either agrees or refuses request Next participant performs the activity / action: The initiator is informed of the result / completion of the action or that the action has failed.

22. Example: Subscribe Protocol Initiator subscribes to the participant. Participant either agrees or refuses subscription Participant informs initiator of any information relating to the subscription or sends a failure message if necessary.

23. Example: Brokering Protocol

24. Example: Recruit Protocol