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

Many reality tasks such as robot coordination can be naturally modelled asmulti-agent cooperative system where the rewards are sparse. This paper focuseson learning decentralized policies for such tasks using sub-optimaldemonstration. To learn the multi-agent cooperation effectively and tackle thesub-optimality of demonstration, a self-improving learning method is proposed:On the one hand, the centralized state-action values are initialized by thedemonstration and updated by the learned decentralized policy to improve thesub-optimality. On the other hand, the Nash Equilibrium are found by thecurrent state-action value and are used as a guide to learn the policy. Theproposed method is evaluated on the combat RTS games which requires a highlevel of multi-agent cooperation. Extensive experimental results on variouscombat scenarios demonstrate that the proposed method can learn multi-agentcooperation effectively. It significantly outperforms many state-of-the-artdemonstration based approaches.

Cooperative Multi-Agent Policy Gradients with Sub-optimal Demonstration