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

Offline reinforcement learning (RL) has received considerable attention inrecent years due to its attractive capability of learning policies from offlinedatasets without environmental interactions. Despite some success in thesingle-agent setting, offline multi-agent RL (MARL) remains to be a challenge.The large joint state-action space and the coupled multi-agent behaviors poseextra complexities for offline policy optimization. Most existing offline MARLstudies simply apply offline data-related regularizations on individual agents,without fully considering the multi-agent system at the global level. In thiswork, we present OMIGA, a new offline m ulti-agent RL algorithm with implicitglobal-to-local v alue regularization. OMIGA provides a principled framework toconvert global-level value regularization into equivalent implicit local valueregularizations and simultaneously enables in-sample learning, thus elegantlybridging multi-agent value decomposition and policy learning with offlineregularizations. Based on comprehensive experiments on the offline multi-agentMuJoCo and StarCraft II micro-management tasks, we show that OMIGA achievessuperior performance over the state-of-the-art offline MARL methods in almostall tasks.

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization