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

This work considers the problem of learning cooperative policies inmulti-agent settings with partially observable and non-stationary environmentswithout a communication channel. We focus on improving information sharingbetween agents and propose a new multi-agent actor-critic method called\textit{Multi-Agent Cooperative Recurrent Proximal Policy Optimization}(MACRPO). We propose two novel ways of integrating information across agentsand time in MACRPO: First, we use a recurrent layer in critic's networkarchitecture and propose a new framework to use a meta-trajectory to train therecurrent layer. This allows the network to learn the cooperation and dynamicsof interactions between agents, and also handle partial observability. Second,we propose a new advantage function that incorporates other agents' rewards andvalue functions. We evaluate our algorithm on three challenging multi-agentenvironments with continuous and discrete action spaces, Deepdrive-Zero,Multi-Walker, and Particle environment. We compare the results with severalablations and state-of-the-art multi-agent algorithms such as QMIX and MADDPGand also single-agent methods with shared parameters between agents such asIMPALA and APEX. The results show superior performance against otheralgorithms. The code is available online athttps://github.com/kargarisaac/macrpo.

MACRPO: Multi-Agent Cooperative Recurrent Policy Optimization