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

We study provable multi-agent reinforcement learning (MARL) in the generalframework of partially observable stochastic games (POSGs). To circumvent theknown hardness results and the use of computationally intractable oracles, weadvocate leveraging the potential \emph{information-sharing} among agents, acommon practice in empirical MARL, and a standard model for multi-agent controlsystems with communications. We first establish several computation complexityresults to justify the necessity of information-sharing, as well as theobservability assumption that has enabled quasi-efficient single-agent RL withpartial observations, for computational efficiency in solving POSGs. We thenpropose to further \emph{approximate} the shared common information toconstruct an {approximate model} of the POSG, in which planning an approximateequilibrium (in terms of solving the original POSG) can be quasi-efficient,i.e., of quasi-polynomial-time, under the aforementioned assumptions.Furthermore, we develop a partially observable MARL algorithm that is bothstatistically and computationally quasi-efficient. We hope our study may openup the possibilities of leveraging and even designing different\emph{information structures}, for developing both sample- andcomputation-efficient partially observable MARL.

Partially Observable Multi-agent RL with (Quasi-)Efficiency: The Blessing of Information Sharing