Tensor Decomposition for Multi-agent Predictive State Representation
Tensor Decomposition for Multi-agent Predictive State Representation
复制标题
DOI：
10.1016/j.eswa.2021.115969
复制
发表时间：
2020-05
期刊：
影响因子：
--
通讯作者：
Bilian Chen;Biyang Ma;Yi-feng Zeng;Langcai Cao;Jing Tang
中科院分区：
文献类型：
--
作者：
Bilian Chen;Biyang Ma;Yi-feng Zeng;Langcai Cao;Jing Tang
预测状态表示 (PSR) 使用动作观察序列向量来表示系统动态，并随后预测未来事件的概率。它是一种简洁的知识表示，在单智能体规划问题领域得到了充分研究。据我们所知，目前还没有使用 PSR 来解决多智能体规划问题的工作。学习多智能体 PSR 模型非常困难，尤其是随着智能体数量的不断增加，更不用说问题域的复杂性了。在本文中，我们采用张量技术来解决多智能体 PSR 模型开发问题的挑战性任务。首先关注双智能体设置，我们将系统动力学矩阵构造为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并推导状态向量，并通过线性回归导出转移参数。随后我们在多智能体环境中推广 PSR 学习方法。实验结果表明，我们的方法可以有效解决多个问题域中的多智能体PSR建模问题。
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.