This article presents two new algorithms for finding the optimal solution of a Multi-agent Multi-objective Reinforcement Learning problem. Both algorithms make use of the concepts of modularization and acceleration by a ...

A multi-agent methodology is proposed for Decentralized Reinforcement Learning (DRL) of individual behaviors in problems where multi-dimensional action spaces are involved. When using this methodology, sub-tasks are learned ...

O presente trabalho tem como motivação principal o estudo de modelos de aprendizado por reforço multi-agent, comumente utilizados quando o problema é episódico e a dinâmica do sistema é complexa de ser descrita analiticamente, ...

This article presents two new algorithms for finding the optimal solution of a Multi-agent Multi-objective Reinforcement Learning problem. Both algorithms make use of the concepts of modularization and acceleration by a ...

On-line learning methods have been applied successfully in multi-agent systems to achieve coordination among agents. Learning in multi-agent systems implies in a non-stationary scenario perceived by the agents, since the ...

Recent developments in Reinforcement Learning (RL) methods are focused on models that can learn good policies in non stationary environments, such as multi-agent games, where agents must learn how to react to changes in ...

We propose a new paradigm for collective learning in multi-agent systems (MAS) as a solution to the problem in which several agents acting over the same environment must learn how to perform tasks, simultaneously, based ...

Los sistemas multi-agente han mostrado, por su propia naturaleza, permitir resolver problemas que requieren coordinaci´on y/o cooperaci´on, ello por cuanto permiten representar de forma natural dichas situaciones. Sin ...

This paper addresses the design and implementation of complex Reinforcement Learning (RL) behaviors where multi-dimensional action spaces are involved, as well as the need to execute the behaviors in real-time using robotic ...