An Exploration for higher efficiency in multi objective optimisation with reinforcement learning

Efficiency in optimisation and search processes remain one of the challenges, which affects the performance and use of optimisation algorithms. Use of multiple operators to move within a neighbourhood looks more promising, but an optimum or near optimum sequence of operators requires further investigation, while lots of work is done for single objective optimisation, but multi-objective cases remain more challenging. A multi-agent reinforcement learning approach looks promising to tackle this problem and offer good solutions. This work introduces an prototype work in this regard, which helps demonstrate the efficiency of using multi-agent reinforcement learning.