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

Learning to collaborate is critical in Multi-Agent Reinforcement Learning(MARL). Previous works promote collaboration by maximizing the correlation ofagents' behaviors, which is typically characterized by Mutual Information (MI)in different forms. However, we reveal sub-optimal collaborative behaviors alsoemerge with strong correlations, and simply maximizing the MI can,surprisingly, hinder the learning towards better collaboration. To address thisissue, we propose a novel MARL framework, called Progressive Mutual InformationCollaboration (PMIC), for more effective MI-driven collaboration. PMIC uses anew collaboration criterion measured by the MI between global states and jointactions. Based on this criterion, the key idea of PMIC is maximizing the MIassociated with superior collaborative behaviors and minimizing the MIassociated with inferior ones. The two MI objectives play complementary rolesby facilitating better collaborations while avoiding falling into sub-optimalones. Experiments on a wide range of MARL benchmarks show the superiorperformance of PMIC compared with other algorithms.

PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration