Tennant, Elizaveta;
Hailes, Stephen;
Musolesi, Mirco;
(2024)
Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents.
In: Das, Sanmay and Green, Brian Patrick and Varshney, Kush and Ganapini, Marianna and Renda, Andrea, (eds.)
Proceedings of the Seventh AAAI/ACM Conference on AI, Ethics, and Society (AIES-24).
(pp. pp. 1444-1454).
AAAI Press: San Jose, California, USA.
Preview |
Text
2403.04202v7.pdf - Accepted Version Download (3MB) | Preview |
Abstract
Growing concerns about safety and alignment of AI systems highlight the importance of embedding moral capabilities in artificial agents: a promising solution is the use of learning from experience, i.e., Reinforcement Learning. In multi-agent (social) environments, complex population-level phenomena may emerge from interactions between individual learning agents. Many of the existing studies rely on simulated social dilemma environments to study the interactions of independent learning agents; however, they tend to ignore the moral heterogeneity that is likely to be present in societies of agents in practice. For example, at different points in time a single learning agent may face opponents who are consequentialist (i.e., focused on maximizing outcomes over time), norm-based (i.e., conforming to specific norms), or virtue-based (i.e., considering a combination of different virtues). The extent to which agents' co-development may be impacted by such moral heterogeneity in populations is not well understood. In this paper, we present a study of the learning dynamics of morally heterogeneous populations interacting in a social dilemma setting. Using an Iterated Prisoner's Dilemma environment with a partner selection mechanism, we investigate the extent to which the prevalence of diverse moral agents in populations affects individual agents' learning behaviors and emergent population-level outcomes. We observe several types of non-trivial interactions between pro-social and anti-social agents, and find that certain types of moral agents are able to steer selfish agents towards more cooperative behavior.
| Type: | Proceedings paper |
|---|---|
| Title: | Dynamics of Moral Behavior in Heterogeneous Populations of Learning Agents |
| Event: | 7th AAAI/ACM Conference on AI, Ethics, and Society (AIES-24) |
| Location: | San Jose, California, USA |
| Dates: | 21 Oct 2024 - 23 Oct 2024 |
| ISBN: | 10 1-57735-892-9 |
| ISBN-13: | 978-1-57735-892-3 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1609/aies.v7i1.31736 |
| Publisher version: | https://ojs.aaai.org/index.php/AIES/article/view/3... |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10204690 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
