Dual Observation Self-paced Policy Co-Training
This repository is a work in progress. It builds off of the work conducted by Ma, et al. (2020) in their original paper of Self-paced Multi-view Co-training (SPaMCo) [1]. It has been adapted to learn a policy for a Markov decision process through reinforcement learning. The foundation of this work was taken from the repository constructed by Ma, et al. below:
https://github.com/Flowerfan/SPamCo
Any use or reference of this repository must conform to the licenses established by Ma, et al. on their repository. Any citation of this work must also cite the work of Ma, et al. below:
@article{JMLR:v21:18-794,
author = {Fan Ma and Deyu Meng and Xuanyi Dong and Yi Yang},
title = {Self-paced Multi-view Co-training},
journal = {Journal of Machine Learning Research},
year = {2020},
volume = {21},
number = {57},
pages = {1-38},
url = {http://jmlr.org/papers/v21/18-794.html}
}
References:
[1] Fan Ma, Deyu Meng, Xuany Dong, and Yi Yang. Self-paced Multi-view Co-training. Journal of Machine Learning Research, pages 1-38, 2020. https://jmlr.org/papers/volume21/18-794/18-794.pdf