Affiliations: School of Computer, Northwestern Polytechnical University, Beilin District, Xi’an Shaanxi, P.R. China
Correspondence:
[*]
Corresponding author. Zhu Yi-an, School of Computer, Northwestern Polytechnical University, 127 West Youyi Road, Beilin District, Xi’an Shaanxi, 710072, P.R. China. E-mail: zhuya@nwpu.edu.cn.
Abstract: Transfer learning has been identified as conducive to improving the speed of machine learning in many areas. In multi-task reinforcement learning, transfer learning can assist the transfer of experiences between different tasks. The research conducted in this article is focused on two aspects. On the one hand, multi-task parallel transfer learning can improve the learning speed of parallel learning tasks. On the other hand, the learning of the current optimal experience can help the target point rewards to be transmitted to the starting point. The value of this self-learning can also accelerate the convergence speed of the reinforcement learning. According to the research into these two aspects, this paper uses the idea of particle swarm optimization (PSO) to conduct self-learning and interactive learning in multi-task parallel learning. In this paper, a new multi-task learning algorithm named PSO-MTPRL (Multi-Task Parallel Reinforcement Learning based on PSO) is proposed. Based on the idea of PSO algorithm, the Boltzmann strategy, Self-Learning Process (SLP) and Interactive Learning Process (ILP) are selected probabilistically. Based on the characteristic exhibited by reinforcement learning, segmented learning model is recommended. In the early learning stages, the complete Boltzmann exploration strategy is applied, and B-SLP-ILP (Boltzmann-SLP- ILP) learning procedure is conducted exclusively in the middle stage of the learning. In the late learning stages, Boltzmann exploration is involved again. The segmented learning model can help ensure the balance of the exploration and exploitation, in addition to ensuring that all tasks convergence.
