Explore the Context: Optimal Data Collection for Context-Conditional Dynamics Models
Max Planck Institute for Intelligent Systems(马克斯·普朗克智能系统研究所)
Jan Achterhold, Joerg Stueckler
备注:
Accepted for publication at the 24th International Conference on Artificial Intelligence and Statistics (AISTATS) 2021, with supplementary material. Corrected version (see footnote on p. 6)
In this paper, we learn dynamics models for parametrized families of dynamical systems with varying properties. The dynamics models are formulated as stochastic processes conditioned on a latent context variable which is inferred from observed transitions of the respective system. The probabilistic formulation allows us to compute an action sequence which, for a limited number of environment interactions, optimally explores the given system within the parametrized family. This is achieved by steering the system through transitions being most informative for the context variable. We demonstrate the effectiveness of our method for exploration on a non-linear toy-problem and two well-known reinforcement learning environments.
Parameter-Free and Group Conditional Online Conformal Prediction
Data Science and AI Institute (DSAI), Johns Hopkins University(数据科学与人工智能研究院(DSAI),约翰霍普金斯大学);Mathematical Institute for Data Science (MINDS), Johns Hopkins University(数据科学数学研究院(MINDS),约翰霍普金斯大学);Department of Biomedical Engineering, Johns Hopkins University(生物医学工程系,约翰霍普金斯大学);Department of Computer Science, Johns Hopkins University(计算机科学系,约翰霍普金斯大学);Amazon Responsible AI(亚马逊负责任人工智能)
Pretrained-Guided Conditional Diffusion Models for Microbiome Data Analysis
School of Information Science and Engineering, Yunnan University(云南大学信息科学与工程学院);College of Nursing Health Sciences, Yunnan Open University(云南开放大学护理与健康科学学院)