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 2302.09465cs.LG
收藏

随机生成流网络

Stochastic Generative Flow Networks

Mila - Québec AI Institute(米拉-魁北克人工智能研究所);Université de Montréal(蒙特利尔大学);Tsinghua University(清华大学)

Ling Pan, Dinghuai Zhang, Moksh Jain, Longbo Huang, Yoshua Bengio

AI总结:

本文提出Stochastic GFlowNets算法,通过将状态转移分解为两步以分离环境随机性并学习动力学模型,成功将GFlowNets扩展至随机环境,在多个标准基准上显著优于现有方法。

摘要:

生成流网络(简称GFlowNets)是一类概率智能体,通过“推断即控制”的视角学习采样复杂的组合结构。它们在从给定的能量景观中生成高质量且多样的候选对象方面展现了巨大潜力。然而,现有的GFlowNets仅能应用于确定性环境,在具有随机动力学的更一般任务中会失败,这可能限制其适用性。为克服这一挑战,本文引入了Stochastic GFlowNets,这是一种将GFlowNets扩展到随机环境的新算法。通过将状态转移分解为两个步骤,Stochastic GFlowNets分离了环境的随机性,并学习一个动力学模型来捕捉它。大量实验结果表明,在多种具有随机动力学的标准基准上,Stochastic GFlowNets相比标准GFlowNets以及基于MCMC和RL的方法具有显著优势。

英文摘要:

Generative Flow Networks (or GFlowNets for short) are a family of probabilistic agents that learn to sample complex combinatorial structures through the lens of "inference as control". They have shown great potential in generating high-quality and diverse candidates from a given energy landscape. However, existing GFlowNets can be applied only to deterministic environments, and fail in more general tasks with stochastic dynamics, which can limit their applicability. To overcome this challenge, this paper introduces Stochastic GFlowNets, a new algorithm that extends GFlowNets to stochastic environments. By decomposing state transitions into two steps, Stochastic GFlowNets isolate environmental stochasticity and learn a dynamics model to capture it. Extensive experimental results demonstrate that Stochastic GFlowNets offer significant advantages over standard GFlowNets as well as MCMC- and RL-based approaches, on a variety of standard benchmarks with stochastic dynamics.

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。

↑