Here - Agents Lab - University of Nottingham

Recommendations

Info

Evaluation of a Conversation ManagementToolkit for Multi Agent ProgrammingDavid Lillis, Rem W. Collier, and Howell R. JordanSchool of Computer Science and InformaticsUniversity College Dublin{david.lillis,rem.collier}@ucd.iehowell.jordan@lero.ieAbstract. The Agent Conversation Reasoning Engine (ACRE) is intendedto aid agent developers with the management of conversationsto improve the management and reliability of agent communication. Toevaluate its effectiveness, a problem was presented to two groups of undergraduatestudents, one of which was required to create a solutionusing the features of ACRE and one without.This paper describes the requirements that the evaluation scenario wasintended to meet and how these motivated the design of the problemthat was presented to the subjects. The solutions were analysed usinga combination of simple objective metrics and subjective analysis,which indicated a number of benefits of using ACRE. In particular, subjectiveanalysis suggested that ACRE by defaults prevents some commonproblems arising that would limit the reliability and extensibility ofconversation-handling code.1 IntroductionThe Agent Conversation Reasoning Engine (ACRE) is a suite of components andtools to aid the developers of agent oriented software systems to handle interagentcommunication in a more structured and reliable manner [1]. To date,ACRE has been integrated into the Agent Factory multi-agent framework [2]and is available for use with any of the agent programming languages supportedby Agent Factory’s Common Language Framework [3]. Related work is presentedin Section 2, followed by an overview of ACRE itself in Section 3.The principal focus of this paper is to describe an experiment that was conductedto evaluate the benefits that ACRE can provide in a communicationheavyMAS. Section 4 outlines the motivations underpinning the design of theexperiment and discusses how a scenario was designed with these in mind. Inparticular, we identified a number of variables that should be eliminated so asto ensure that comparisons of ACRE and non-ACRE code would be fair. Thisscenario was given to a class of undergraduate students, who were required todevelop agents that could interact with a number of provided agents in orderto trade virtual stocks and properties for profit. The subjects were divided intotwo groups: one using ACRE and one working without.85
The code was analysed both objectively and subjectively and comparisonswere made between code written using ACRE and code written without ACRE.This analysis is presented in Section 5. We then examined some conversationhandling code written for the Jason multi agent platform to draw some conclusionsabout the wider applicability of this work in Section 6. Conclusions andideas for future work are contained in Section 7.2 Related WorkAlthough many well-known agent frameworks and languages have support forsome Agent Communication Language (ACL), less attention has been paid to thenotion of conversations between agents, where two or more agents will exchangemultiple messages that are related to the same topic or subject, following apre-defined protocol. The JADE toolkit provides specific implementations of anumber of the FIPA interaction protocols [4]. It also provides a Finite StateMachine (FSM) behaviour to allow custom interaction protocols to be definedin terms of how they are handled by the agents. Jason includes native supportfor communicative acts, but does not provide specific tools for the developmentof agent conversations using interaction protocols. A similar level of supporthas previously been present within the Agent Factory framework prior to theadoption of ACRE.Agent toolkits with support for conversations include COOL [5], Jackal [6]and KaOS [7]. Other than FSMs, alternative representations for protocols includeColoured Petri Nets [8] and Dooley Graphs [9].The comparative evaluation of programming toolkits, paradigms and languagesis a matter of some debate within the software engineering community.One popular approach is to divide subjects into two groups with each askedto perform the same task [10–12]. To the greatest extent possible, objectivequantitative measures are used to draw comparisons between the two groups.A common concept to evaluate is that of programmer effort, which has beenmeasured in numerous different ways including development time [10, 11], noncommentline count [11] and non-commented source code statements [13]. Thesemeasures are used to ensure that a new approach does not result in a greaterworkload being placed on developers using it.3 ACREACRE is a framework that aims to give agent programmers greater control overthe management of conversations within their MASs. It is motivated by thefact that many widely-used AOP languages/frameworks require communicationto be handled on a message-by-message basis, with no explicit link betweenrelated messages. It frequently tends to be left as an exercise for the developer86
Page 2 and 3:
Proceedings of the Tenth Internatio
Page 4 and 5:
OrganisationOrganising CommitteeMeh
Page 6:
Table of ContentseJason: an impleme
Page 10 and 11:
in Sect. 3 the translation of the J
Page 12 and 13:
init_count(0).max_count(2000).(a)(b
Page 14 and 15:
For instance, a failure in the ERES
Page 16 and 17:
{plan, fun start_count_trigger/1,fu
Page 18 and 19:
single parameter, an Erlang record
Page 20 and 21:
1. Belief annotations. Even though
Page 22 and 23:
decisions taken during the design a
Page 24 and 25:
Conceptual Integration of Agents wi
Page 26 and 27:
Fig. 2. Active component structurep
Page 28 and 29:
the service provider component. As
Page 30 and 31:
Fig. 4. Web Service Invocationretri
Page 32 and 33:
01: public interface IBankingServic
Page 34 and 35:
tate them in the same way as in the
Page 36 and 37: 01: public interface IChartService
Page 38 and 39: implementations being available for
Page 41: deliberative behavior in BDI archit
Page 44 and 45: layer modules (i.e. nodes) can be d
Page 46 and 47: different methods to choose the cur
Page 48 and 49: also a single scheduler module, imp
Page 50 and 51: andom choice (OR), conditional choi
Page 52 and 53: - Dealing with conflicts based on p
Page 54 and 55: 5. Brooks, R. A. (1991) Intelligenc
Page 56 and 57: An Agent-Based Cognitive Robot Arch
Page 58 and 59: It has been argued that building ro
Page 60 and 61: EnvironmentHardwareLocal SoftwareC+
Page 62 and 63: a cognitive layer can connect as a
Page 64 and 65: can reliably be differentiated and
Page 66 and 67: 4 ExperimentTo evaluate the feasibi
Page 68 and 69: learn or gain knowledge from experi
Page 70 and 71: A Programming Framework for Multi-A
Page 72 and 73: exchange and storage of tuples (key
Page 74 and 75: Although some success [13] [14] hav
Page 76 and 77: as well as important non-functional
Page 78 and 79: component plans have been instantia
Page 80 and 81: A in the example) can evaluate all
Page 83 and 84: 1. robot-1 issues a Localization(ro
Page 85: ACKNOWLEDGMENTThis work has been su
Page 89 and 90: a conversation is following. Additi
Page 91 and 92: the context of a communication-heav
Page 93 and 94: Table 1. Core Agent ProtocolsAgent
Page 95 and 96: statistically significant using an
Page 97 and 98: to the conversation and has a perfo
Page 99 and 100: principal reasons. Firstly, it is a
Page 101 and 102: 2. Muldoon, C., O’Hare, G.M.P., C
Page 103 and 104: In the following section we will at
Page 105 and 106: DevelopmentProductionHuman Readabil
Page 107 and 108: will then evaluate this new format
Page 109 and 110: encoder, it is first checked if the
Page 111 and 112: nents themselves. However, since th
Page 113 and 114: optimized for this format feature s
Page 115 and 116: Java serialization and Jadex Binary
Page 117 and 118: 10. P. Hoffman and F. Yergeau, “U
Page 119 and 120: Caching the results of previous que
Page 121 and 122: querying an agent’s beliefs and g
Page 123 and 124: or relative performance of each pla
Page 125 and 126: were run for 1.5 minutes; 1.5 minut
Page 127 and 128: Size N K n p c qry U c upd Update c
Page 129 and 130: epresentation. The cache simply act
Page 131 and 132: 6 ConclusionWe presented an abstrac
Page 133 and 134: Typing Multi-Agent Programs in simp
Page 135 and 136: 1 // agent ag02 iterations (" zero
Page 137 and 138:
3.1 simpAL OverviewThe main inspira
Page 139 and 140:
3.2 Typing Agents with Tasks and Ro
Page 141 and 142:
Defining Agent Scripts in simpAL (F
Page 143 and 144:
that sends a message to the receive
Page 145 and 146:
* error: wrong type for the param v
Page 147 and 148:
Given an organization model, it is
Page 149 and 150:
Learning to Improve Agent Behaviour
Page 151 and 152:
2.1 Agent Programming LanguagesAgen
Page 153 and 154:
choosing actions is to find a good
Page 155 and 156:
1 init module {2 knowledge{3 block(
Page 157 and 158:
of a module. For example, to change
Page 159 and 160:
if bel(on(X,Y), clear(X)), a-goal(c
Page 161 and 162:
mance. Figure 2d shows the same A f
Page 163 and 164:
the current percepts of the agent.
Page 165:
Author IndexAbdel-Naby, S., 69Alelc
show all

Here - Agents Lab - University of Nottingham

You also want an ePaper? Increase the reach of your titles

Delete template?

Save as template?