Learning Predictive State Representations in Dynamical Systems Without Reset

Abstract

Predictive state representations (PSRs) are a recently-developed way to model discrete-time, controlled dynamical systems. We present and describe two algorithms for learning a PSR model: a Monte Carlo algorithm and a temporal difference (TD) algorithm. Both of these algorithms can learn models for systems without requiring a reset action as was needed by the previously available general PSR-model learning algorithm. We present empirical results that compare our two algorithms and also compare their performance with that of existing algorithms, including an EM algorithm for learning POMDP models.

Cite

Text

Wolfe et al. "Learning Predictive State Representations in Dynamical Systems Without Reset." International Conference on Machine Learning, 2005. doi:10.1145/1102351.1102475

Markdown

[Wolfe et al. "Learning Predictive State Representations in Dynamical Systems Without Reset." International Conference on Machine Learning, 2005.](https://mlanthology.org/icml/2005/wolfe2005icml-learning/) doi:10.1145/1102351.1102475

BibTeX

@inproceedings{wolfe2005icml-learning,
  title     = {{Learning Predictive State Representations in Dynamical Systems Without Reset}},
  author    = {Wolfe, Britton and James, Michael R. and Singh, Satinder},
  booktitle = {International Conference on Machine Learning},
  year      = {2005},
  pages     = {980-987},
  doi       = {10.1145/1102351.1102475},
  url       = {https://mlanthology.org/icml/2005/wolfe2005icml-learning/}
}