Self-governance by Transfiguration: From Learning to Prescriptions

详细信息    查看全文

• 作者：Régis Riveret (23)
  Alexander Artikis (24)
  Dídac Busquets (23)
  Jeremy Pitt (23)
  
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8554
• 期：1
• 页码：177-191
• 全文大小：528 KB
• 参考文献：1. ?gotnes, T., Wooldridge, M.: Optimal social laws. In: AAMAS, pp. 667-74 (2010)
  2. Broersen, J., Dastani, M., Hulstijn, J., Huang, Z., van der Torre, L.: The boid architecture: Conflicts between beliefs, obligations, intentions and desires. In: Proceedings of the Fifth International Conference on Autonomous Agents, AGENTS 2001, pp. 9-6. ACM, New York (2001) CrossRef
  3. Castelfranchi, C., Giardini, F., Lorini, E., Tummolini, L.: The prescriptive destiny of predictive attitudes: from expectations to norms via conventions. In: Proceedings of CogSci 2003, 25th Annual Meeting of the Cognitive Science Society (2003)
  4. Christelis, G., Rovatsos, M., Petrick, R.P.A.: Exploiting domain knowledge to improve norm synthesis. In: AAMAS, pp. 831-38 (2010)
  5. Esteva, M., Rodriguez-Aguilar, J., Arcos, J., Sierra, C., Garcia, P.: Institutionalising open multi-agent systems. In: Durfee, E. (ed.) Proceedings of the International Conference on Multi-agent Systems (ICMAS), pp. 381-82. IEEE Press (2000)
  6. Fitoussi, D., Tennenholtz, M.: Choosing social laws for multi-agent systems: minimality and simplicity. Artificial Intelligence?119(1-2), 61-01 (2000) CrossRef
  7. Governatori, G., Rotolo, A.: Bio logical agents: Norms, beliefs, intentions in defeasible logic. Autonomous Agents and Multi-Agent Systems?17(1), 36-9 (2008) CrossRef
  8. Morales, J., López-Sánchez, M., Rodríguez-Aguilar, J.A.: Michael Wooldridge, and Wamberto Vasconcelos, ‘Automated synthesis of normative systems- In: AAMAS, pp. 483-90 (2013)
  9. Partalas, I., Feneris, I., Vlahavas, I.P.: Multi-agent reinforcement learning using strategies and voting. In: ICTAI (2), pp. 318-24. IEEE Computer Society
  10. Mitchell Polinsky, A., Shavell, S.: Handbook of Law and Economics, 1st edn., vol.?1. Elsevier (2007)
  11. Riveret, R., Rotolo, A., Sartor, G.: ‘Probabilistic rule-based argumentation for norm-governed learning agents- Artif. Intell?20(4), 383-20 (2012)
  12. Andrighetto, G., Conte, R., Campennl, M.: Minding Norms: Mechanisms and dynamics of social order in agent societies. Oxford Scholarship (2013)
  13. Sartor, G.: Legal Reasoning: A Cognitive Approach to Law. Springer (2005)
  14. Sen, S., Airiau, S.: Emergence of norms through social learning. In: Proceedings of the 20th International Joint Conference on Artifical Intelligence, IJCAI 2007, pp. 1507-512. Morgan Kaufmann Publishers Inc., San Francisco (2007)
  15. Shoham, Y., Tennenholtz, M.: ‘On social laws for artificial agent societies: off-line design- Artificial Intelligence?73(1-2), 231-52 (1995) CrossRef
  16. Sutton, R.S., Barto, A.G.: Reinforcement learning: An introduction, vol.?116. Cambridge Univ. Press (1998)
  
• 作者单位：Régis Riveret (23)
  Alexander Artikis (24)
  Dídac Busquets (23)
  Jeremy Pitt (23)
  
  23. Imperial College London, United Kingdom
  24. NCSR Demokritos, Greece
  
• ISSN：1611-3349

文摘

Norms are commonly understood as guides for the conduct of autonomous agents, thereby easing their individual decision-making and coordination. However, their study exhibits a polarity between (i) norms as behavioural patterns emerging from repeated agents-(inter)actions and (ii) norms as explicit prescriptions. In this paper, we attempt to build a bridge between these two conceptual poles of norms: it takes the form of a mental function for prescriptive transfiguration allowing reinforced learning agents to express their learning experiences into prescriptions. The population of transfigurative agents are then equipped with a consensus system to build and enforce prescriptive systems to self-govern on-line. Simple simulations suggest the pertinence of the approach and shows its weaknesses, in particular prescriptions stalling learning, and timeliness in norm construction.