Bibliog.bib

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%VARIABLES%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%
%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%BIBLIOGRAPHY%%%%%%%%%%%%%%%%%%%%%%%%%%
@incollection{akiyama2013helios,
  title={HELIOS base: An open source package for the robocup soccer 2d simulation},
  author={Akiyama, Hidehisa and Nakashima, Tomoharu},
  booktitle={RoboCup 2013: Robot World Cup XVII},
  pages={528--535},
  year={2013},
  publisher={Springer}
}
@article{hinton2006reducing,
  title={Reducing the dimensionality of data with neural networks},
  author={Hinton, Geoffrey E and Salakhutdinov, Ruslan R},
  journal={Science},
  volume={313},
  number={5786},
  pages={504--507},
  year={2006},
  publisher={American Association for the Advancement of Science}
}
@article{bengio2007greedy,
  title={Greedy layer-wise training of deep networks},
  author={Bengio, Yoshua and Lamblin, Pascal and Popovici, Dan and Larochelle, Hugo and others},
  journal={Advances in neural information processing systems},
  volume={19},
  pages={153},
  year={2007},
  publisher={MIT; 1998}
}
@inproceedings{silver2014deterministic,
  title={Deterministic policy gradient algorithms},
  author={Silver, David and Lever, Guy and Heess, Nicolas and Degris, Thomas and Wierstra, Daan and Riedmiller, Martin},
  booktitle={ICML},
  year={2014}
}
@article{lillicrap2015continuous,
  title={Continuous control with deep reinforcement learning},
  author={Lillicrap, Timothy P and Hunt, Jonathan J and Pritzel, Alexander and Heess, Nicolas and Erez, Tom and Tassa, Yuval and Silver, David and Wierstra, Daan},
  journal={arXiv preprint arXiv:1509.02971},
  year={2015}
}
@article{mnih2015human,
  title={Human-level control through deep reinforcement learning},
  author={Mnih, Volodymyr and Kavukcuoglu, Koray and Silver, David and Rusu, Andrei A and Veness, Joel and Bellemare, Marc G and Graves, Alex and Riedmiller, Martin and Fidjeland, Andreas K and Ostrovski, Georg and others},
  journal={Nature},
  volume={518},
  number={7540},
  pages={529--533},
  year={2015},
  publisher={Nature Publishing Group}
}
@book{sutton1998reinforcement,
  title={Reinforcement learning: An introduction},
  author={Sutton, Richard S and Barto, Andrew G},
  year={1998},
  publisher={MIT press}
}
@article{van1978discounted,
  title={Discounted Markov games: generalized policy iteration method},
  author={Van Der Wal, J},
  journal={Journal of Optimization Theory and Applications},
  volume={25},
  number={1},
  pages={125--138},
  year={1978},
  publisher={Springer}
}
@inproceedings{precup2001off,
  title={Off-policy temporal-difference learning with function approximation},
  author={Precup, Doina and Sutton, Richard S and Dasgupta, Sanjoy},
  booktitle={ICML},
  pages={417--424},
  year={2001}
}
@article{barto2004j,
  title={J. 4 supervised actor-critic reinforcement learning},
  author={BARTO, MTRAG},
  journal={Handbook of learning and approximate dynamic programming},
  volume={2},
  pages={359},
  year={2004},
  publisher={John Wiley \& Sons}
}
@inproceedings{sutton1999policy,
  title={Policy Gradient Methods for Reinforcement Learning with Function Approximation.},
  author={Sutton, Richard S and McAllester, David A and Singh, Satinder P and Mansour, Yishay and others},
  booktitle={NIPS},
  volume={99},
  pages={1057--1063},
  year={1999}
}
@inproceedings{claus1998dynamics,
  title={The dynamics of reinforcement learning in cooperative multiagent systems},
  author={Claus, Caroline and Boutilier, Craig},
  booktitle={AAAI/IAAI},
  pages={746--752},
  year={1998}
}
@incollection{yang2010multi,
  title={Multi-layer Perceptron},
  author={Yang, Zheng Rong},
  booktitle={Machine Learning Approaches To Bioinformatics},
  pages={133--153},
  year={2010},
  publisher={World Scientific}
}
@article{hinton2010practical,
  title={A practical guide to training restricted Boltzmann machines},
  author={Hinton, Geoffrey},
  journal={Momentum},
  volume={9},
  number={1},
  pages={926},
  year={2010}
}
@article{erhan2010does,
  title={Why does unsupervised pre-training help deep learning?},
  author={Erhan, Dumitru and Bengio, Yoshua and Courville, Aaron and Manzagol, Pierre-Antoine and Vincent, Pascal and Bengio, Samy},
  journal={The Journal of Machine Learning Research},
  volume={11},
  pages={625--660},
  year={2010},
  publisher={JMLR. org}
}
% ---------------------------------------------------------------------