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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

QTRAN is a multi-agent reinforcement learning (MARL) algorithm capable oflearning the largest class of joint-action value functions up to date. However,despite its strong theoretical guarantee, it has shown poor empiricalperformance in complex environments, such as Starcraft Multi-Agent Challenge(SMAC). In this paper, we identify the performance bottleneck of QTRAN andpropose a substantially improved version, coined QTRAN++. Our gains come from(i) stabilizing the training objective of QTRAN, (ii) removing the strict roleseparation between the action-value estimators of QTRAN, and (iii) introducinga multi-head mixing network for value transformation. Through extensiveevaluation, we confirm that our diagnosis is correct, and QTRAN++ successfullybridges the gap between empirical performance and theoretical guarantee. Inparticular, QTRAN++ newly achieves state-of-the-art performance in the SMACenvironment. The code will be released.

QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning