Cooperative Multi-Robot Hierarchical Reinforcement Learning

Recent advances in multi-robot deep reinforcement learning have made it possible to perform efficient exploration in problem space, but it remains a significant challenge in many complex domains. To alleviate this problem, a hierarchical approach has been designed in which agents can operate at many...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:International journal of advanced computer science & applications Jg. 13; H. 9
Hauptverfasser: Setyawan, Gembong Edhi, Hartono, Pitoyo, Sawada, Hideyuki
Format: Journal Article
Sprache:Englisch
Veröffentlicht: West Yorkshire Science and Information (SAI) Organization Limited 2022
Schlagworte:
Deep learning
Multiagent systems
Multiple robots
Policies
Robots
ISSN:2158-107X, 2156-5570
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recent advances in multi-robot deep reinforcement learning have made it possible to perform efficient exploration in problem space, but it remains a significant challenge in many complex domains. To alleviate this problem, a hierarchical approach has been designed in which agents can operate at many levels to complete tasks more efficiently. This paper proposes a novel technique called Multi-Agent Hierarchical Deep Deterministic Policy Gradient that combines the benefits of multiple robot systems with the hierarchical system used in Deep Reinforcement Learning. Here, agents acquire the ability to decompose a problem into simpler subproblems with varying time scales. Furthermore, this study develops a framework to formulate tasks into multiple levels. The upper levels function to learn policies for defining lower levels’ subgoals, whereas the lowest level depicts robot’s learning policies for primitive actions in the real environment. The proposed method is implemented and validated in a modified Multiple Particle Environment (MPE) scenario.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2158-107X
2156-5570
DOI:10.14569/IJACSA.2022.0130904