paper-with-me

Papers

Learning about a changing state

2024-01-07 · Benjamin Davies

A long-lived Bayesian agent observes costly signals of a time-varying state. He chooses the signals' precisions sequentially, balancing their costs and marginal informativeness. I compare the optimal myopic and forward-looking precisions when the state follows a Brownian motion. I also compare the myopic precisions induced by other Gaussian processes.

📄 PDF Abstract BibTeX arXiv:2401.03607

Code (0)

등록된 구현이 없습니다.

Tasks

Gaussian ProcessesInformativeness

Similar Papers 제목 키워드 기반

Video State-Changing Object Segmentation

2023-01-01 · ICCV 2023 1 · Jiangwei Yu, Xiang Li, Xinran Zhao, Hongming Zhang 외

Daily objects commonly experience state changes. For example, slicing a cucumber changes its state from whole to sliced. Learning about object state changes in Video Object Segmentation (VOS) is crucial for understan…

ObjectRepresentation LearningSegmentationSemantic Segmentation+2

Learning from Neighbors about a Changing State

2018-01-06 · Krishna Dasaratha, Benjamin Golub, Nir Hak

Agents learn about a changing state using private signals and their neighbors' past estimates of the state. We present a model in which Bayesian agents in equilibrium use neighbors' estimates simply by taking weighted su…

Diversity

Intelligent Control of Merging Car-following and Lane-Changing Behavior

2025-03-09 · Farzam Tajdari, Amin Rezasoltani

Recent research has paid little attention to complex driving behaviors, namely merging car-following and lane-changing behavior, and how lane-changing affects algorithms designed to model and control a car-following vehi…

Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Deep Reinforcement Learning

2026-06-10 · Felix Störck, Fabian Hinder, Barbara Hammer arxiv

Studies on rodents such as mice have shown the capabilities to adapt their behavior when dealing with changing parameters (``drift'') of the environment even if no information about change is provided (uncertainty) -- a …

Reinforcement Learning

Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains

2021-10-29 · NeurIPS 2021 12 · Christian Gumbsch, Martin V. Butz, Georg Martius

A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors. We hypothes…

Inductive Bias