Runtime Revision of Norms and Sanctions based on Agent Preferences. Dell'Anna, D., Dastani, M., & Dalpiaz, F. In Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2019, pages 1609–1617, 2019. Link Paper Slides Poster abstract bibtex 1 download To fulfill the overall objectives of a multiagent system, the behavior of individual agents should be controlled and coordinated. Runtime norm enforcement is one way to do so without over-constraining the agents' autonomy. Due to the dynamicity and uncertainty of the environment, however, it is hard to specify norms that, when enforced, will fulfill the system-level objectives in every operating context. In this paper, we propose a mechanism for the automated revision of norms by altering their sanctions, based on the data monitored during the system execution and on some knowledge about the agents' preferences. We use a Bayesian Network to learn at runtime the relationship between the obedience of a norm and the achievement of the system objectives. We propose two heuristic strategies that explore the updated Bayesian Network and automatically revise the sanction of an enforced norm. An evaluation of our heuristics using a traffic simulator shows that our mechanisms outperform uninformed heuristics in terms of convergence speed.
@inproceedings{DBLP:conf/atal/DellAnnaDD19,
author = {Davide Dell'Anna and
Mehdi Dastani and
Fabiano Dalpiaz},
title = {Runtime Revision of Norms and Sanctions based on Agent Preferences},
booktitle = {Proceedings of the 18th International Conference on Autonomous Agents
and MultiAgent Systems, {AAMAS} 2019},
pages = {1609--1617},
year = {2019},
url_Link = {http://dl.acm.org/citation.cfm?id=3331881},
url_Paper = {2019_AAMAS/AAMAS19_DellAnna.pdf},
url_Slides= {2019_AAMAS/AAMAS19_DellAnna_Slides.pdf},
url_Poster= {2019_AAMAS/AAMAS19_DellAnna_Poster.pdf},
keywords = {Norm Revision, Norms, MAS, Multi-Agent Systems, Sanctions, Preferences, Data Driven Supervision Of Autonomous Systems},
timestamp = {Wed, 29 May 2019 16:36:58 +0200},
biburl = {https://dblp.org/rec/conf/atal/DellAnnaDD19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org},
abstract = {To fulfill the overall objectives of a multiagent system, the behavior of individual agents should be controlled and coordinated. Runtime norm enforcement is one way to do so without over-constraining the agents' autonomy. Due to the dynamicity and uncertainty of the environment, however, it is hard to specify norms that, when enforced, will fulfill the system-level objectives in every operating context. In this paper, we propose a mechanism for the automated revision of norms by altering their sanctions, based on the data monitored during the system execution and on some knowledge about the agents' preferences. We use a Bayesian Network to learn at runtime the relationship between the obedience of a norm and the achievement of the system objectives. We propose two heuristic strategies that explore the updated Bayesian Network and automatically revise the sanction of an enforced norm. An evaluation of our heuristics using a traffic simulator shows that our mechanisms outperform uninformed heuristics in terms of convergence speed.}
}
Downloads: 1
{"_id":"Z4WdP77RFxABWhych","bibbaseid":"dellanna-dastani-dalpiaz-runtimerevisionofnormsandsanctionsbasedonagentpreferences-2019","authorIDs":["btfox5LNCYjybS6FG"],"author_short":["Dell'Anna, D.","Dastani, M.","Dalpiaz, F."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Davide"],"propositions":[],"lastnames":["Dell'Anna"],"suffixes":[]},{"firstnames":["Mehdi"],"propositions":[],"lastnames":["Dastani"],"suffixes":[]},{"firstnames":["Fabiano"],"propositions":[],"lastnames":["Dalpiaz"],"suffixes":[]}],"title":"Runtime Revision of Norms and Sanctions based on Agent Preferences","booktitle":"Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2019","pages":"1609–1617","year":"2019","url_link":"http://dl.acm.org/citation.cfm?id=3331881","url_paper":"2019_AAMAS/AAMAS19_DellAnna.pdf","url_slides":"2019_AAMAS/AAMAS19_DellAnna_Slides.pdf","url_poster":"2019_AAMAS/AAMAS19_DellAnna_Poster.pdf","keywords":"Norm Revision, Norms, MAS, Multi-Agent Systems, Sanctions, Preferences, Data Driven Supervision Of Autonomous Systems","timestamp":"Wed, 29 May 2019 16:36:58 +0200","biburl":"https://dblp.org/rec/conf/atal/DellAnnaDD19.bib","bibsource":"dblp computer science bibliography, https://dblp.org","abstract":"To fulfill the overall objectives of a multiagent system, the behavior of individual agents should be controlled and coordinated. Runtime norm enforcement is one way to do so without over-constraining the agents' autonomy. Due to the dynamicity and uncertainty of the environment, however, it is hard to specify norms that, when enforced, will fulfill the system-level objectives in every operating context. In this paper, we propose a mechanism for the automated revision of norms by altering their sanctions, based on the data monitored during the system execution and on some knowledge about the agents' preferences. We use a Bayesian Network to learn at runtime the relationship between the obedience of a norm and the achievement of the system objectives. We propose two heuristic strategies that explore the updated Bayesian Network and automatically revise the sanction of an enforced norm. An evaluation of our heuristics using a traffic simulator shows that our mechanisms outperform uninformed heuristics in terms of convergence speed.","bibtex":"@inproceedings{DBLP:conf/atal/DellAnnaDD19,\n author = {Davide Dell'Anna and\n Mehdi Dastani and\n Fabiano Dalpiaz},\n title = {Runtime Revision of Norms and Sanctions based on Agent Preferences},\n booktitle = {Proceedings of the 18th International Conference on Autonomous Agents\n and MultiAgent Systems, {AAMAS} 2019},\n pages = {1609--1617},\n year = {2019},\n url_Link = {http://dl.acm.org/citation.cfm?id=3331881},\n url_Paper = {2019_AAMAS/AAMAS19_DellAnna.pdf},\n url_Slides= {2019_AAMAS/AAMAS19_DellAnna_Slides.pdf},\n url_Poster= {2019_AAMAS/AAMAS19_DellAnna_Poster.pdf},\n keywords = {Norm Revision, Norms, MAS, Multi-Agent Systems, Sanctions, Preferences, Data Driven Supervision Of Autonomous Systems},\n timestamp = {Wed, 29 May 2019 16:36:58 +0200},\n biburl = {https://dblp.org/rec/conf/atal/DellAnnaDD19.bib},\n bibsource = {dblp computer science bibliography, https://dblp.org},\n abstract = {To fulfill the overall objectives of a multiagent system, the behavior of individual agents should be controlled and coordinated. Runtime norm enforcement is one way to do so without over-constraining the agents' autonomy. Due to the dynamicity and uncertainty of the environment, however, it is hard to specify norms that, when enforced, will fulfill the system-level objectives in every operating context. In this paper, we propose a mechanism for the automated revision of norms by altering their sanctions, based on the data monitored during the system execution and on some knowledge about the agents' preferences. We use a Bayesian Network to learn at runtime the relationship between the obedience of a norm and the achievement of the system objectives. We propose two heuristic strategies that explore the updated Bayesian Network and automatically revise the sanction of an enforced norm. An evaluation of our heuristics using a traffic simulator shows that our mechanisms outperform uninformed heuristics in terms of convergence speed.}\n}\n\n\n\n","author_short":["Dell'Anna, D.","Dastani, M.","Dalpiaz, F."],"key":"DBLP:conf/atal/DellAnnaDD19","id":"DBLP:conf/atal/DellAnnaDD19","bibbaseid":"dellanna-dastani-dalpiaz-runtimerevisionofnormsandsanctionsbasedonagentpreferences-2019","role":"author","urls":{" link":"http://dl.acm.org/citation.cfm?id=3331881"," paper":"http://davidedellanna.com/publications/2019_AAMAS/AAMAS19_DellAnna.pdf"," slides":"http://davidedellanna.com/publications/2019_AAMAS/AAMAS19_DellAnna_Slides.pdf"," poster":"http://davidedellanna.com/publications/2019_AAMAS/AAMAS19_DellAnna_Poster.pdf"},"keyword":["Norm Revision","Norms","MAS","Multi-Agent Systems","Sanctions","Preferences","Data Driven Supervision Of Autonomous Systems"],"metadata":{"authorlinks":{"dell'anna, d":"https://bibbase.org/show?bib=https://dblp.org/pid/201/0398.bib"}},"downloads":1,"html":""},"bibtype":"inproceedings","biburl":"http://davidedellanna.com/publications/dellanna.bib","creationDate":"2021-02-08T09:40:40.443Z","downloads":1,"keywords":["norm revision","norms","mas","multi-agent systems","sanctions","preferences","data driven supervision of autonomous systems"],"search_terms":["runtime","revision","norms","sanctions","based","agent","preferences","dell'anna","dastani","dalpiaz"],"title":"Runtime Revision of Norms and Sanctions based on Agent Preferences","year":2019,"dataSources":["Rymgh7KJx3EhNfvG8","6mqXRucaPuwqWyQEd","2pnuieZznE6L96taK"]}