Advances in variational inference

C Zhang, J Bütepage, H Kjellström… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Many modern unsupervised or semi-supervised machine learning algorithms rely on
Bayesian probabilistic models. These models are usually intractable and thus require …

Dynamical variational autoencoders: A comprehensive review

L Girin, S Leglaive, X Bie, J Diard, T Hueber… - ar**: Toward the robust-perception age
C Cadena, L Carlone, H Carrillo, Y Latif… - IEEE Transactions …, 2016 - ieeexplore.ieee.org
Simultaneous localization and map** (SLAM) consists in the concurrent construction of a
model of the environment (the map), and the estimation of the state of the robot moving …

Learning latent dynamics for planning from pixels

D Hafner, T Lillicrap, I Fischer… - International …, 2019 - proceedings.mlr.press
Planning has been very successful for control tasks with known environment dynamics. To
leverage planning in unknown environments, the agent needs to learn the dynamics from …

Deep state space models for time series forecasting

SS Rangapuram, MW Seeger… - Advances in neural …, 2018 - proceedings.neurips.cc
We present a novel approach to probabilistic time series forecasting that combines state
space models with deep learning. By parametrizing a per-time-series linear state space …

Model-based reinforcement learning: A survey

TM Moerland, J Broekens, A Plaat… - … and Trends® in …, 2023 - nowpublishers.com
Sequential decision making, commonly formalized as Markov Decision Process (MDP)
optimization, is an important challenge in artificial intelligence. Two key approaches to this …

KalmanNet: Neural network aided Kalman filtering for partially known dynamics

G Revach, N Shlezinger, X Ni… - IEEE Transactions …, 2022 - ieeexplore.ieee.org
State estimation of dynamical systems in real-time is a fundamental task in signal
processing. For systems that are well-represented by a fully known linear Gaussian state …

Stochastic latent actor-critic: Deep reinforcement learning with a latent variable model

AX Lee, A Nagabandi, P Abbeel… - Advances in Neural …, 2020 - proceedings.neurips.cc
Deep reinforcement learning (RL) algorithms can use high-capacity deep networks to learn
directly from image observations. However, these high-dimensional observation spaces …