Multi-objective reinforcement learning algorithm and its application in drive system

Generally, reinforcement learning (RL) is used to design neurocontroller for control system with single objective. When facing multi-objective system, it is necessary to design the neurocontroller according to the personal preference. This paper proposed a multi-objective reinforcement learning algorithm (MORLA) to design neurocontroller with the personal preference. It transformed the multi-objective into synthetical objective and applied parallel genetic algorithm (PGA) to evolve the neurocontroller according to the synthetical objective. To establish the synthetical objective, the objective weight which represents the personal preference is calculated by solving the constrained optimization problem (COP) at the end of each generation. The COP requires not only the biggest variance of the synthetical objective in the population, but also requires the weight to fit the designerpsilas preference. After acquiring the weights, the PGA can select the elitists from the population according to the designerpsilas preference and design a satisfying neurocontroller by evolutionary operations. At last, the MORLA is used to design neurocontroller for a speed-controlled induction motor drive with indirect vector control. This paper designed several neurocontrollers with different personal preferences for the drive system. The simulation results show the feasibility and validity of the MORLA.