arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.13706cs.LGcs.MA
收藏

基于张量分解的多智能体预测状态表示

Tensor Decomposition for Multi-agent Predictive State Representation

Xiamen University(厦门大学);Teesside University(提赛德大学)

Bilian Chen, Biyang Ma, Yifeng Zeng, Langcai Cao, Jing Tang

摘要:

预测状态表示(PSR)是用一个动作-观测序列向量来表示系统的动态特性,并预测未来事件发生的概率。它是一种简洁的知识表示,在单智能体规划问题域中得到了很好的研究。据我们所知,目前还没有使用PSR解决多智能体规划问题的工作。学习多智能体PSR模型是相当困难的,特别是随着智能体数量的增加,更不用说问题域的复杂性。在本文中,我们诉诸张量技术来解决具有挑战性的任务,多智能体PSR模型开发问题。首先针对两个智能体的情况,构造系统动力学矩阵作为PSR模型的高阶张量,分别通过两种不同的张量分解方法直接学习预测参数和推导状态向量,并通过线性回归得到过渡参数。随后,我们概括了PSR学习方法在多智能体设置。实验结果表明,我们的方法可以有效地解决多个问题域的多智能体PSR建模问题。

英文摘要:

Predictive state representation~(PSR) uses a vector of action-observation sequence to represent the system dynamics and subsequently predicts the probability of future events. It is a concise knowledge representation that is well studied in a single-agent planning problem domain. To the best of our knowledge, there is no existing work on using PSR to solve multi-agent planning problems. Learning a multi-agent PSR model is quite difficult especially with the increasing number of agents, not to mention the complexity of a problem domain. In this paper, we resort to tensor techniques to tackle the challenging task of multi-agent PSR model development problems. By first focusing on a two-agent setting, we construct the system dynamics matrix as a high order tensor for a PSR model, learn the prediction parameters and deduce state vectors directly through two different tensor decomposition methods respectively, and derive the transition parameters via linear regression. Subsequently, we generalize the PSR learning approaches in a multi-agent setting. Experimental results show that our methods can effectively solve multi-agent PSR modelling problems in multiple problem domains.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑