# Learning to track environment state via predictive autoencoding

arXiv: https://arxiv.org/abs/2112.07745 · HTML: https://mlsanity.com/paper/2112.07745/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 14 Dec 2021.

## Builds on (most cited first, 11 of 11)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm](https://mlsanity.com/paper/1712.01815/) (2017)
- [Unsupervised Learning of Video Representations using LSTMs](https://mlsanity.com/paper/1502.04681/) (2015)
- [Deep multi-scale video prediction beyond mean square error](https://mlsanity.com/paper/1511.05440/) (2015)
- [Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning](https://mlsanity.com/paper/1605.08104/) (2016)
- [Action-Conditional Video Prediction using Deep Networks in Atari Games](https://mlsanity.com/paper/1507.08750/) (2015)
- [Unsupervised Learning of Visual Structure using Predictive Generative Networks](https://mlsanity.com/paper/1511.06380/) (2015)
- [A Long Short-Term Memory Recurrent Neural Network Framework for Network Traffic Matrix Prediction](https://mlsanity.com/paper/1705.05690/) (2017)
- [Prediction Under Uncertainty with Error-Encoding Networks](https://mlsanity.com/paper/1711.04994/) (2017)

## Abstract (arXiv)

This work introduces a neural architecture for learning forward models of stochastic environments. The task is achieved solely through learning from temporal unstructured observations in the form of images. Once trained, the model allows for tracking of the environment state in the presence of noise or with new percepts arriving intermittently. Additionally, the state estimate can be propagated in observation-blind mode, thus allowing for long-term predictions. The network can output both expectation over future observations and samples from belief distribution. The resulting functionalities are similar to those of a Particle Filter (PF). The architecture is evaluated in an environment where we simulate objects moving. As the forward and sensor models are available, we implement a PF to gauge the quality of the models learnt from the data.