Learning Approximate Stochastic Transition Models

By Pichao Wang, Wanqing Li, Jun Wan, Philip O. Ogunbona, Xinwang Liu. 2017

25 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Jun Liu
2. Wanqing Li
3. Pichao Wang
4. Qiuhong Ke
5. Philip O. Ogunbona
6. Hossein Rahmani
7. Zehua Sun
8. Sergio Escalera

In Statistical and Nonlinear Physics

1. Jun Wan
2. Wanqing Li
3. Hossein Rahmani
4. Sergio Escalera

Citations in the corpus

• RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “[154] proposed to cooperatively train a single convolutional neural network (named c-ConvNet) on both RGB and depth features, and deeply aggregate the two kinds of features for action recognition.”
• Human Action Recognition From Various Data Modalities: A Review (2020, methodology): “some other works as representations of videos for HAR [56], [57], [58].”