Learning Curve Bounds for a Markov Decision Process with Undiscounted Rewards

Saul and Singh. "Learning Curve Bounds for a Markov Decision Process with Undiscounted Rewards." Annual Conference on Computational Learning Theory, 1996. doi:10.1145/238061.238084

[Saul and Singh. "Learning Curve Bounds for a Markov Decision Process with Undiscounted Rewards." Annual Conference on Computational Learning Theory, 1996.](https://mlanthology.org/colt/1996/saul1996colt-learning/) doi:10.1145/238061.238084

@inproceedings{saul1996colt-learning,
  title     = {{Learning Curve Bounds for a Markov Decision Process with Undiscounted Rewards}},
  author    = {Saul, Lawrence K. and Singh, Satinder P.},
  booktitle = {Annual Conference on Computational Learning Theory},
  year      = {1996},
  pages     = {147-156},
  doi       = {10.1145/238061.238084},
  url       = {https://mlanthology.org/colt/1996/saul1996colt-learning/}
}