Authors:
Kun Qian
;
Robert W. Brehm
and
Lars Duggen
Affiliation:
SDU Mechatronics, Mads Clausen Institute, University of Southern Denmark and Denmark
Keyword(s):
Cooperative Multi-Agent Systems, Multi-Agent Reinforcement Learning, Multi-Agent Actor-Critic, Cooperative Navigation, Simulation Based Learning.
Related
Ontology
Subjects/Areas/Topics:
Agents
;
Artificial Intelligence
;
Artificial Intelligence and Decision Support Systems
;
Computational Intelligence
;
Cooperation and Coordination
;
Distributed and Mobile Software Systems
;
Enterprise Information Systems
;
Evolutionary Computing
;
Industrial Applications of AI
;
Knowledge Discovery and Information Retrieval
;
Knowledge Engineering and Ontology Development
;
Knowledge-Based Systems
;
Machine Learning
;
Multi-Agent Systems
;
Robot and Multi-Robot Systems
;
Self Organizing Systems
;
Soft Computing
;
Software Engineering
;
Symbolic Systems
Abstract:
A method for simulation based reinforcement learning (RL) for a multi-agent system acting in a physical environment is introduced, which is based on Multi-Agent Actor-Critic (MAAC) reinforcement learning. In the proposed method, avatar agents learn in a simulated model of the physical environment and the learned experience is then used by agents in the actual physical environment. The proposed concept is verified using a laboratory benchmark setup in which multiple agents, acting within the same environment, are required to coordinate their movement actions to prevent collisions. Three state-of-the-art algorithms for multi-agent reinforcement learning (MARL) are evaluated, with respect to their applicability for a predefined benchmark scenario. Based on simulations it is shown that the MAAC method is most applicable for implementation as it provides effective distributed learning and suits well to the concept of learning in simulated environments. Our experimental results, which comp
are simulated learning and task execution in a simulated environment with that of task execution in a physical environment demonstrate the feasibility of the proposed concept.
(More)