English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Society is characterized by the presence of a variety of social norms:collective patterns of sanctioning that can prevent miscoordination andfree-riding. Inspired by this, we aim to construct learning dynamics wherepotentially beneficial social norms can emerge. Since social norms areunderpinned by sanctioning, we introduce a training regime where agents canaccess all sanctioning events but learning is otherwise decentralized. Thissetting is technologically interesting because sanctioning events may be theonly available public signal in decentralized multi-agent systems where rewardor policy-sharing is infeasible or undesirable. To achieve collective action inthis setting we construct an agent architecture containing a classifier modulethat categorizes observed behaviors as approved or disapproved, and amotivation to punish in accord with the group. We show that social norms emergein multi-agent systems containing this agent and investigate the conditionsunder which this helps them achieve socially beneficial outcomes.

A learning agent that acquires social norms from public sanctions in decentralized multi-agent settings