Near-Optimal Reinforcement Learning in Polynominal Time

Kearns and Singh. "Near-Optimal Reinforcement Learning in Polynominal Time." International Conference on Machine Learning, 1998.

[Kearns and Singh. "Near-Optimal Reinforcement Learning in Polynominal Time." International Conference on Machine Learning, 1998.](https://mlanthology.org/icml/1998/kearns1998icml-near/)

@inproceedings{kearns1998icml-near,
  title     = {{Near-Optimal Reinforcement Learning in Polynominal Time}},
  author    = {Kearns, Michael J. and Singh, Satinder},
  booktitle = {International Conference on Machine Learning},
  year      = {1998},
  pages     = {260-268},
  url       = {https://mlanthology.org/icml/1998/kearns1998icml-near/}
}