arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.12964cs.AIstat.ML
收藏

论主动推理与控制作为推理的关系

On the Relationship Between Active Inference and Control as Inference

University of Edinburgh(爱丁堡大学);University of Sussex(苏塞克斯大学)

Beren Millidge, Alexander Tschantz, Anil K Seth, Christopher L Buckley

摘要:

主动推理(AIF)是脑科学中的一个新兴框架,它表明生物因子的作用是最小化模型证据的变分边界。控制即推理(CAI)是强化学习中的一个框架,它将决策问题转化为变分推理问题。虽然这些框架都考虑通过变分推理的镜头动作选择,它们的关系仍然不清楚。在这里,我们提供了它们之间的正式比较,并证明了主要的差异来自于价值如何被纳入各自的生成模型。在这种比较的背景下,我们强调了这些框架可以相互告知的几种方式。

英文摘要:

Active Inference (AIF) is an emerging framework in the brain sciences which suggests that biological agents act to minimise a variational bound on model evidence. Control-as-Inference (CAI) is a framework within reinforcement learning which casts decision making as a variational inference problem. While these frameworks both consider action selection through the lens of variational inference, their relationship remains unclear. Here, we provide a formal comparison between them and demonstrate that the primary difference arises from how value is incorporated into their respective generative models. In the context of this comparison, we highlight several ways in which these frameworks can inform one another.

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。

↑