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

Recent works have applied the Proximal Policy Optimization (PPO) to themulti-agent cooperative tasks, such as Independent PPO (IPPO); and vanillaMulti-agent PPO (MAPPO) which has a centralized value function. However,previous literature shows that MAPPO may not perform as well as Independent PPO(IPPO) and the Fine-tuned QMIX on Starcraft Multi-Agent Challenge (SMAC).MAPPO-Feature-Pruned (MAPPO-FP) improves the performance of MAPPO by thecarefully designed agent-specific features, which may be not friendly toalgorithmic utility. By contrast, we find that MAPPO may face the problem of\textit{The Policies Overfitting in Multi-agent Cooperation(POMAC)}, as theylearn policies by the sampled advantage values. Then POMAC may lead to updatingthe multi-agent policies in a suboptimal direction and prevent the agents fromexploring better trajectories. In this paper, to mitigate the multi-agentpolicies overfitting, we propose a novel policy regularization method, whichdisturbs the advantage values via random Gaussian noise. The experimentalresults show that our method outperforms the Fine-tuned QMIX, MAPPO-FP, andachieves SOTA on SMAC without agent-specific features. We open-source the codeat \url{https://github.com/hijkzzz/noisy-mappo}.

Policy Regularization via Noisy Advantage Values for Cooperative Multi-agent Actor-Critic methods