Reinforcement Learning of Normative Monitoring Intensities

Jiaqi Li, Felipe Meneguzzi, Moser Silva Fagundes, Brian Logan

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

2 Citations (Scopus)

Abstract

Choosing actions within norm-regulated environments involves balancing achieving one's goals and coping with any penalties for non-compliant behaviour. This choice becomes more complicated in environments where there is uncertainty. In this paper, we address the question of choosing actions in environments where there is uncertainty regarding both the outcomes of agent actions and the intensity of monitoring for norm violations. Our technique assumes no prior knowledge of probabilities over action outcomes or the likelihood of norm violations being detected by employing reinforcement learning to discover both the dynamics of the environment and the effectiveness of the enforcer. Results indicate agents become aware of greater rewards for violations when enforcement is lax, which gradually become less attractive as the enforcement is increased.
Original languageEnglish
Title of host publicationCoordination, Organizations, Institutions, and Norms in Agent Systems XI.
Subtitle of host publicationCOIN 2015
PublisherSpringer
Pages209-223
Number of pages15
DOIs
Publication statusPublished - May 2015

Publication series

NameLecture Notes in Computer Science
Volume9628

Fingerprint

Dive into the research topics of 'Reinforcement Learning of Normative Monitoring Intensities'. Together they form a unique fingerprint.

Cite this