Date: 2013
Type: Contribution to book
Vicarious reinforcement and ex ante law enforcement : a study in norm-governed learning agents
Enrico FRANCESCONI and Bart VERHEIJ (eds), Proceedings of the fourteenth international conference on artificial intelligence and law, [S.l.] : ACM, 2013, pp. 222-226
RIVERET, Régis, CONTISSA, Giuseppe, BUSQUETS, Dídac, ROTOLO, Antonino, PITT, Jeremy, SARTOR, Giovanni, Vicarious reinforcement and ex ante law enforcement : a study in norm-governed learning agents, in Enrico FRANCESCONI and Bart VERHEIJ (eds), Proceedings of the fourteenth international conference on artificial intelligence and law, [S.l.] : ACM, 2013, pp. 222-226
- https://hdl.handle.net/1814/30362
Retrieved from Cadmus, EUI Research Repository
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.
Cadmus permanent link: https://hdl.handle.net/1814/30362
Full-text via DOI: 10.1145/2514601.2514631
ISBN: 9781450320801
Files associated with this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |