A multi-agent cooperative reinforcement learning model using a hierarchy of consultants, tutors and workers

Abstract

The hierarchical organisation of distributed sys-tems can provide an efficient decomposition for machine learning. This paper proposes an algorithm for coopera-tive policy construction for independent learners, named Q-learning with aggregation (QA-learning). The algorithm is based on a distributed hierarchical learning model and utilises three specialisations of agents: workers, tutors and consul-tants. The consultant agent incorporates the entire system in its problem space, which it decomposes into sub-problems that are assigned to the tutor and worker agents. The QA-learning algorithm aggregates the Q-tables of worker agents into a central repository managed by their tutor agent. Each tutor's Q-table is then incorporated into the consultant's Q-table, resulting in a Q-table for the entire problem. The algorithm was tested using a distributed hunter prey problem, and experimental results show that QA-learning converges to a solution faster than single agent Q-learning and some famous cooperative Q-learning algorithms.