论文标题
深入推论学习感知和计划
Learning Perception and Planning with Deep Active Inference
论文作者
论文摘要
主动推断是大脑的过程理论，该理论指出所有生物体都推断作用以最大程度地减少其（预期的）自由能。但是，当前的实验仅限于预定义的，通常是离散的状态空间。在本文中，我们利用最新的深度学习进步来学习状态空间，并近似必要的概率分布以进行主动推断。
Active inference is a process theory of the brain that states that all living organisms infer actions in order to minimize their (expected) free energy. However, current experiments are limited to predefined, often discrete, state spaces. In this paper we use recent advances in deep learning to learn the state space and approximate the necessary probability distributions to engage in active inference.
