Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs

Cite

Text

Szita and Lörincz. "Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs." International Conference on Machine Learning, 2009. doi:10.1145/1553374.1553502

Markdown

[Szita and Lörincz. "Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs." International Conference on Machine Learning, 2009.](https://mlanthology.org/icml/2009/szita2009icml-optimistic/) doi:10.1145/1553374.1553502

BibTeX

@inproceedings{szita2009icml-optimistic,
  title     = {{Optimistic Initialization and Greediness Lead to Polynomial Time Learning in Factored MDPs}},
  author    = {Szita, Istvan and Lörincz, András},
  booktitle = {International Conference on Machine Learning},
  year      = {2009},
  pages     = {1001-1008},
  doi       = {10.1145/1553374.1553502},
  url       = {https://mlanthology.org/icml/2009/szita2009icml-optimistic/}
}