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

Multi-Agent Reinforcement Learning (MARL) is a widely used technique foroptimization in decentralised control problems. However, most applications ofMARL are in static environments, and are not suitable when agent behaviour andenvironment conditions are dynamic and uncertain. Addressing uncertainty insuch environments remains a challenging problem for MARL-based systems. Thedynamic nature of the environment causes previous knowledge of how agentsinteract to become outdated. Advanced knowledge of potential changes throughprediction significantly supports agents converging to near-optimal controlsolutions. In this paper we propose P-MARL, a decentralised MARL algorithmenhanced by a prediction mechanism that provides accurate information regardingup-coming changes in the environment. This prediction is achieved by employingan Artificial Neural Network combined with a Self-Organising Map that detectsand matches changes in the environment. The proposed algorithm is validated ina realistic smart-grid scenario, and provides a 92% Pareto efficient solutionto an electric vehicle charging problem.

Decentralised Multi-Agent Reinforcement Learning for Dynamic and Uncertain Environments