A Systematic Approach for Including Machine Learning in Multi-agent Systems

Large scale multi-agent systems (MASs) in unpredictable environments must use machine learning techniques to perform their goals and improve the performance of the system. This paper presents a systematic approach to introduce machine learning in the design and implementation phases of a software agent. We also present an incremental implementation process for building asynchronous and distributed agents, which enable the combination of machine learning strategies. This process supports the stepwise building of adaptable MASs for unknown situations, improving their capacity to scale up. We use the Trading Agent Competition (TAC) environment as a case study to illustrate the suitability of our approach.