# Learning Approximate Stochastic Transition Models

arXiv: https://arxiv.org/abs/1710.09718 · HTML: https://mlsanity.com/paper/1710.09718/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Oct 2017.

## Built on by (most cited first, 3 of 3)

- [Trear: Transformer-based RGB-D Egocentric Action Recognition](https://mlsanity.com/paper/2101.03904/) (2021)
- [Modality Mixer for Multi-modal Action Recognition](https://mlsanity.com/paper/2208.11314/) (2022)
- [Learning Scene Flow With Skeleton Guidance For 3D Action Recognition](https://mlsanity.com/paper/2306.13285/) (2023)

## Abstract (arXiv)

We examine the problem of learning mappings from state to state, suitable for use in a model-based reinforcement-learning setting, that simultaneously generalize to novel states and can capture stochastic transitions. We show that currently popular generative adversarial networks struggle to learn these stochastic transition models but a modification to their loss functions results in a powerful learning algorithm for this class of problems.