用神经网络高效追踪复杂系统的隐藏状态分布。
Neural Bayesian Filtering
- 用嵌入向量表示信念，结合生成模型采样
- 在三个部分可观测环境中实现准确状态估计
- 适合需要快速多模态状态推断的强化学习场景
我们提出神经贝叶斯滤波（Neural Bayesian Filtering, NBF），一种在部分可观测系统中维护隐藏状态分布（即信念）的算法。NBF通过训练学习任务诱导的信念的优良潜在表示，将信念映射为固定长度的嵌入向量，用于条件生成模型采样。在滤波过程中，基于粒子的更新方法在该嵌入空间中利用观测数据和环境动态计算后验分布。NBF融合了经典滤波的计算效率与深度生成模型的表达能力，在保持快速变化的多模态信念的同时，缓解了粒子贫化问题。我们在三个部分可观测环境中的状态估计任务上验证了NBF的有效性。
原文摘要 · Abstract (English)
We present Neural Bayesian Filtering (NBF), an algorithm for maintaining distributions over hidden states, called beliefs, in partially observable systems. NBF is trained to find a good latent representation of the beliefs induced by a task. It maps beliefs to fixed-length embedding vectors, which condition generative models for sampling. During filtering, particle-style updates compute posteriors in this embedding space using incoming observations and the environment's dynamics. NBF combines the computational efficiency of classical filters with the expressiveness of deep generative models - tracking rapidly shifting, multimodal beliefs while mitigating the risk of particle impoverishment. We validate NBF in state estimation tasks in three partially observable environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。