Vicarious reinforcement and ex ante law enforcement: a study in norm-governed learning agents

We propose a model of vicarious reinforcement in rule-based learning agents. The influence of this reinforcement is investigated in a population where a law is enforced ex ante. The norm-governed population of learning agents is formalised and simulated in an executable probabilistic rule-based argumentation framework. Vicarious experiences are expressed with rules and their learning effects are integrated into reinforcement learning. So, agents learn not only from their own experiences but also by taking into account the experiences of others. We show that simulation results differ from traditional calculus based on expected utilities.

[1]  R. Cooter,et al.  Law and Economics , 1988 .

[2]  Giulia Andrighetto,et al.  How Agents Find out Norms: A Simulation Based Model of Norm Innovation , 2008, NORMAS.

[3]  Steven Shavell,et al.  A MODEL OF THE OPTIMAL USE OF LIABILITY AND SAFETY REGULATION , 1984 .

[4]  Antonino Rotolo,et al.  Probabilistic rule-based argumentation for norm-governed learning agents , 2012, Artificial Intelligence and Law.

[5]  Alex M. Andrew,et al.  ROBOT LEARNING, edited by Jonathan H. Connell and Sridhar Mahadevan, Kluwer, Boston, 1993/1997, xii+240 pp., ISBN 0-7923-9365-1 (Hardback, 218.00 Guilders, $120.00, £89.95). , 1999, Robotica (Cambridge. Print).

[6]  J. Coleman.  Foundations of Social Theory , 1990 .

[7]  Giuseppe Contissa,et al.  A Study of Ex Ante Law Enforcement in Norm-Governed Learning Agents , 2012, JSAI-isAI Workshops.

[8]  S. Thompson.  Social Learning Theory , 2008 .

[9]  Donald Wittman,et al.  Prior Regulation versus Post Liability: The Choice between Input and Output Monitoring , 1977, The Journal of Legal Studies.

[10]  Jeremy V. Pitt,et al.  Provision and Appropriation of Common-Pool Resources without Full Disclosure , 2012, PRIMA.

[11]  Bastin Tony Roy Savarimuthu,et al.  Norm creation, spreading and emergence: A survey of simulation models of norms in multi-agent systems , 2011, Multiagent Grid Syst..

[12]  Joshua M. Epstein,et al.  Learning to Be Thoughtless: Social Norms and Individual Computation , 2001 .

[13]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[14]  Steven Shavell,et al.  Liability for Harm versus Regulation of Safety , 1983, The Journal of Legal Studies.

[15]  M EpsteinJoshua.  Learning to Be Thoughtless , 2001 .