{"ID":2860467,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.03614","arxiv_id":"2510.03614","title":"Neural Bayesian Filtering","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2510.03614","url_pdf":"https://arxiv.org/pdf/2510.03614v1","authors":"[\"Christopher Solinas\",\"Radovan Haluska\",\"David Sychrovsky\",\"Finbarr Timbers\",\"Nolan Bard\",\"Michael Buro\",\"Martin Schmid\",\"Nathan R. Sturtevant\",\"Michael Bowling\"]","published":"2025-10-04T01:58:55Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"stat.ML\"]","methods":"[]","has_code":false}