arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1709.02341q-bio.NC
收藏

深度主动推理

Deep Active Inference

Kai Ueltzhöffer

摘要:

这项工作结合了认知神经科学的自由能原理和随后的主动推理动力学,以及深度生成模型中变分推理的最新进展,以及引入“深度主动推理”代理的进化策略。该代理最小化其感觉的平均惊喜上的可变自由能约束,这是由稳态参数激发的。它通过优化其感觉输入的生成潜变量模型的参数,以及近似潜变量上的后验分布的变分密度,给定其观察结果,并通过作用于其环境来主动采样可能在此生成模型下的输入。代理的内部动态使用深度和递归神经网络来实现,如在机器学习中所使用的,使得深度主动推理代理成为可扩展且非常灵活的一类主动推理代理。使用山地车的问题,我们展示了如何目标导向的行为可以通过定义适当的先验的潜在状态在代理的模型。此外,我们表明,深度主动推理代理可以学习环境的生成模型,可以从中采样,以了解代理对环境及其相互作用的信念。

英文摘要:

This work combines the free energy principle from cognitive neuroscience and the ensuing active inference dynamics with recent advances in variational inference in deep generative models, and evolution strategies to introduce the "deep active inference" agent. This agent minimises a variational free energy bound on the average surprise of its sensations, which is motivated by a homeostatic argument. It does so by optimising the parameters of a generative latent variable model of its sensory inputs, together with a variational density approximating the posterior distribution over the latent variables, given its observations, and by acting on its environment to actively sample input that is likely under this generative model. The internal dynamics of the agent are implemented using deep and recurrent neural networks, as used in machine learning, making the deep active inference agent a scalable and very flexible class of active inference agent. Using the mountain car problem, we show how goal directed behaviour can be implemented by defining appropriate priors on the latent states in the agent's model. Furthermore, we show that the deep active inference agent can learn a generative model of the environment, which can be sampled from to understand the agent's beliefs about the environment and its interaction therewith.

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。

↑