Dealing with Non-Stationary Environments Using Context Detection

Abstract

In this paper we introduce RL-CD, a method for solving reinforcement learning problems in non-stationary environments. The method is based on a mechanism for creating, updating and selecting one among several partial models of the environment. The partial models are incrementally built according to the system's capability of making predictions regarding a given sequence of observations. We propose, formalize and show the efficiency of this method both in a simple non-stationary environment and in a noisy scenario. We show that RL-CD performs better than two standard reinforcement learning algorithms and that it has advantages over methods specifically designed to cope with non-stationarity. Finally, we present known limitations of the method and future works.

Cite

Text

da Silva et al. "Dealing with Non-Stationary Environments Using Context Detection." International Conference on Machine Learning, 2006. doi:10.1145/1143844.1143872

Markdown

[da Silva et al. "Dealing with Non-Stationary Environments Using Context Detection." International Conference on Machine Learning, 2006.](https://mlanthology.org/icml/2006/dasilva2006icml-dealing/) doi:10.1145/1143844.1143872

BibTeX

@inproceedings{dasilva2006icml-dealing,
  title     = {{Dealing with Non-Stationary Environments Using Context Detection}},
  author    = {da Silva, Bruno Castro and Basso, Eduardo W. and Bazzan, Ana L. C. and Engel, Paulo Martins},
  booktitle = {International Conference on Machine Learning},
  year      = {2006},
  pages     = {217-224},
  doi       = {10.1145/1143844.1143872},
  url       = {https://mlanthology.org/icml/2006/dasilva2006icml-dealing/}
}