@inproceedings{Kwee:01grep,
        title = {Gradient-based Reinforcement Planning in Policy-Search Methods},
        author = {Ivo Kwee and Marcus Hutter and Juergen Schmidhuber},
        booktitle = {Proc. 5th European Workshop on Reinforcement Learning (EWRL-5)},
        pages = {27--29},
        publisher = {Onderwijsinsituut CKI, Utrecht Univ.},
        volume = 27,
        year = 2001,
        url = {http://arxiv.org/abs/cs.AI/0111060},
        id = {2382183},
	priority = {2},
	description = {idsia},
	biburl = {http://www.bibsonomy.org/bibtex/2a92d3c4268771d41b2e7085d4c5f1dc4/schaul},
	keywords = {intelligence, search policy, juergen, gradient, decent, reinforcement, direct, planning, learning, artificial,}
}