Multi-agent Reinforcement Learning Method Based on Observation Reconstruction
Common knowledge is a well-known knowledge set within a multi-agent system.How to make full use of common knowledge for strategic learning is a challenging problem in multi-agent independent learning systems.In addressing this pro-blem,this paper proposes a multi-agent reinforcement learning method called IPPO-CKOR based on observation reconstruction,focusing on common knowledge extraction and independent learning network design.Firstly,the common knowledge features of agents'observation information are computed and fused to obtain fused observation information with common knowledge fea-tures.Secondly,an agent selection algorithm based on common knowledge is used to select closely related agents,and a feature generation mechanism based on reconstruction is employed to construct their feature information.The reconstructed observation information,composed of the fused observation information with common knowledge features,is utilized for learning and execu-ting agent policies.Thirdly,a network structure based on observation reconstruction is designed,which employs multi-head self-attention mechanism to process the reconstructed observation information and uses one-dimensional convolution and GRU layers to handle observation information sequences.This enables the agents to extract more effective features from the observation infor-mation sequences,effectively alleviating the impact of non-stationary environments and partially observable problems.Experimen-tal results demonstrate that the proposed method outperforms existing typical multi-agent reinforcement learning methods that employ independent learning in terms of performance.
NETL
NSTL
万方数据
