关键词: 深度强化学习, RW-MADDPG, 残差网络, 经验池, 围捕奖励函数

Abstract: A multi-agent reinforcement learning algorithm based on improved experience playback is proposed to solve the trapping efficiency problem of multi-agent in non-convex environment. The residual network (ResNet) is used to improve the network degradation problem, and the RW-MADDPG algorithm is proposed by combining with the multi-agent depth Deterministic strategy gradient algorithm (MADDPG). In order to solve the problem of low utilization of experience pool data in non-convex obstacle environment, two methods are proposed to improve the utilization of experience pool data, and a reasonable reward function is designed to make the intelligent ability to complete the rounding task in non-convex obstacle environment. Simulation experiments are designed based on this algorithm. The experimental results show that the algorithm increases the reward faster in the training stage and can complete the rounding task faster. Compared with MADDPG algorithm, the training time is shortened by 18.5% under static rounding environment and 49.1% under dynamic environment. Moreover, the global average reward of the rounding agent trained by this algorithm is higher in the non-convex obstacle environment.

Key words: Deep reinforcement learning, RW-MADDPG, Residual network, Experience pool, Rounding reward function