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

Cooperative multi-agent policy gradient (MAPG) algorithms have recentlyattracted wide attention and are regarded as a general scheme for themulti-agent system. Credit assignment plays an important role in MAPG and caninduce cooperation among multiple agents. However, most MAPG algorithms cannotachieve good credit assignment because of the game-theoretic pathology known as\textit{centralized-decentralized mismatch}. To address this issue, this paperpresents a novel method, \textit{\underline{M}ulti-\underline{A}gent\underline{P}olarization \underline{P}olicy \underline{G}radient} (MAPPG).MAPPG takes a simple but efficient polarization function to transform theoptimal consistency of joint and individual actions into easily realizedconstraints, thus enabling efficient credit assignment in MAPG. Theoretically,we prove that individual policies of MAPPG can converge to the global optimum.Empirically, we evaluate MAPPG on the well-known matrix game and differentialgame, and verify that MAPPG can converge to the global optimum for bothdiscrete and continuous action spaces. We also evaluate MAPPG on a set ofStarCraft II micromanagement tasks and demonstrate that MAPPG outperforms thestate-of-the-art MAPG algorithms.

Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient