@article{twotimescaleconvergentqlearningforsleep,
  title = {Two Timescale Convergent Q-learning for Sleep--Scheduling in Wireless Sensor Networks},
  author = {Prashanth L. A. and Abhranil Chatterjee and Shalabh Bhatnagar},
  year = {2013},
  eprint = {1312.7292},
  archivePrefix = {arXiv},
  url = {http://arxiv.org/abs/1312.7292v2},
}