Active inference provides a general framework for behavior and learning in autonomous agents. It states that an agent will attempt to minimize its variational free energy, defined in terms of beliefs over observations, internal states and policies. Traditionally, every aspect of a discrete active inference model must be specified by hand, i.e. by manually defining the hidden state space structure, as well as the required distributions such as likelihood and transition probabilities. Recently, efforts have been made to learn state space representations automatically from observations using deep neural networks. In this paper, we present a novel approach of learning state spaces using quantum physics-inspired tensor networks. The ability of tensor networks to represent the probabilistic nature of quantum states as well as to reduce large state spaces makes tensor networks a natural candidate for active inference. We show how tensor networks can be used as a generative model for sequential data. Furthermore, we show how one can obtain beliefs from such a generative model and how an active inference agent can use these to compute the expected free energy. Finally, we demonstrate our method on the classic T-maze environment.
翻译:主动推论为自主物剂的行为和学习提供了一个总体框架。 它指出, 代理商将试图将其根据对观测、 内部状态和政策的信念定义的可变自由能量降到最低。 传统上, 一个独立主动推论模型的每个方面都必须由手动指定, 即手动定义隐藏的空间结构, 以及所需的分布, 如可能性和过渡概率。 最近, 努力从使用深层神经网络的观测中自动学习状态空间表现。 本文将展示一种创新的方法, 即使用量子物理激发的抗声网络学习国家空间。 高温网络代表量子状态的概率性质以及减少大型状态空间的能力使强力网络成为主动推论的自然选择。 我们展示了如何将强力网络用作序列数据的基因化模型。 此外, 我们展示了人们如何从这种基因化模型中获得信念, 以及一个积极的推论剂如何使用这些理论来测量预期的自由能源。 最后, 我们展示了我们在典型的Tmaze环境中的方法 。