关键词: 深度强化学习, 确定性策略梯度算法, k-means聚类, 多行动者

Abstract: Aiming at the problems of poor learning performance and high fluctuation in the deep deterministic policy gradient (DDPG) algorithm for tasks with some large state spaces, we proposed a multi-actor deep deterministic policy gradient algorithm based on progressive k-means clustering (MDDPG-PK-Means) algorithm. In the training process, when selecting actions for the state at each time step, the decision-making of the actor network was  assisted based on the discrimination results of  the k-means clustering algorithm. At the same time, as the training steps increased, the number of k-means cluster centers gradually increased. The MDDPG-PK-Means algorithm was applied to the MuJoCo simulation platform, the experimental results show that, compared with 
 DDPG and other algorithms, the MDDPG-PK-Means algorithm has better performance  in most continuous tasks.

Key words: deep reinforcement learning, deterministic policy , gradient algorithm, k-means clustering, multi-actor