计算机应用研究2024，Vol.41Issue(4)：1022-1028,7.DOI:10.19734/j.issn.1001-3695.2023.07.0373
基于图嵌入编码形态信息的非均匀多任务强化学习方法
Method for inhomogeneous multi-task reinforcement learning based on morphological information encoding by graph embedding
摘要
Abstract
Traditional reinforcement learning methods have problems of low efficiency,poor generalization performance,and untransferable policy models.In response to this issue,this paper proposed an inhomogeneous multitask reinforcement learning method,which improved efficiency and generalization performance by learning multiple reinforcement tasks.It constructed the morphology of agent into a graph,and the graph neural network could handle graphs with any connection pattern and size graph,which was really suitable to solve inhomogeneous tasks with different dimensions of state and action space.This breaks through the limitations that model couldn't be transferred and fully utilizes the advantages of graph neural network's natural use of graph structure to induce bias.The model had achieved efficient training and improved generalization performance,and could be quickly migrated to new tasks.The results of multi task learning experiments show that compared with previous methods,this method exhibits better performance in both multi task learning and transfer learning experiments,and exhibits more accurate knowledge transfer in transfer learning experiments.By introducing bias in the structure of the agent graph,this method has achieved higher efficiency and better migration generalization performance.关键词
多任务强化学习/图神经网络/变分图自编码器/形态信息编码/迁移学习Key words
multi-task reinforcement learning/graph neural network/variational graph autoencoder/morphology informa-tion encoding/transfer learning分类
信息技术与安全科学引用本文复制引用
贺晓,王文学..基于图嵌入编码形态信息的非均匀多任务强化学习方法[J].计算机应用研究,2024,41(4):1022-1028,7.基金项目
国家自然科学基金资助项目(U1908215) （U1908215）
辽宁省"兴辽英才计划"资助项目(XLYC2002014) （XLYC2002014）
