Vicarious reinforcement and ex ante law enforcement : a study in norm-governed learning agents
RIVERET, Régis; CONTISSA, Giuseppe; BUSQUETS, Dídac; ROTOLO, Antonino; PITT, Jeremy; SARTOR, Giovanni
Title: Vicarious reinforcement and ex ante law enforcement : a study in norm-governed learning agents
Author: RIVERET, Régis; CONTISSA, Giuseppe; BUSQUETS, Dídac; ROTOLO, Antonino; PITT, Jeremy; SARTOR, Giovanni
Citation: Enrico FRANCESCONI and Bart VERHEIJ (eds), Proceedings of the fourteenth international conference on artificial intelligence and law, [S.l.] : ACM, 2013, pp. 222-226
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.
Files in this item
There are no files associated with this item.