Improved Reinforcement Learning in Cooperative Multi-agent Environments Using Knowledge Transfer

TL;DR

This paper introduces a communication framework with a state reduction method and a knowledge transfer algorithm to improve reinforcement learning efficiency in cooperative multi-agent systems, demonstrated on a shepherding task.

Contribution

It presents a novel framework combining state space reduction and knowledge transfer to enhance learning speed and cooperation among agents in complex environments.

Findings

Accelerated learning process with knowledge transfer

Reduced state space size through state abstraction

Effective cooperation in multi-agent tasks

Abstract

Nowadays, cooperative multi-agent systems are used to learn how to achieve goals in large-scale dynamic environments. However, learning in these environments is challenging: from the effect of search space size on learning time to inefficient cooperation among agents. Moreover, reinforcement learning algorithms may suffer from a long time of convergence in such environments. In this paper, a communication framework is introduced. In the proposed communication framework, agents learn to cooperate effectively and also by introduction of a new state calculation method the size of state space will decline considerably. Furthermore, a knowledge-transferring algorithm is presented to share the gained experiences among the different agents, and develop an effective knowledge-fusing mechanism to fuse the knowledge learnt utilizing the agents' own experiences with the knowledge received from other team members. Finally, the simulation results are provided to indicate the efficacy of the proposed method in the complex learning task. We have evaluated our approach on the shepherding problem and the results show that the learning process accelerates by making use of the knowledge transferring mechanism and the size of state space has declined by generating similar states based on state abstraction concept.