@inproceedings(Abbeel04,
 author       = "Pieter Abbeel and Andrew Y. Ng",
 year         = "2004",
 title        = "Apprenticeship learning via inverse reinforcement learning",
 booktitle    = "International Conference on Machine Learning",
 pages        = "1--",
 doi          = "10.1145/1015330.1015430",
)
@phdthesis(Acar,
 author       = "Umut A. Acar",
 year         = "2005",
 title        = "Self-adjusting computation",
 school       = "Carnegie Mellon University",
 address      = "Pittsburgh, PA, USA",
)
@inproceedings(Andre01,
 author       = "David Andre and Stuart Russell",
 year         = "2001",
 title        = "Programmable Reinforcement Learning Agents",
 booktitle    = "Advances in Neural Information Processing Systems",
 pages        = "1019--1024",
)
@inproceedings(Andre02,
 author       = "David Andre and Stuart Russell",
 year         = "2002",
 title        = "State Abstraction for Programmable Reinforcement Learning Agents",
 booktitle    = "Eighteenth National Conference on Artificial Intelligence",
 pages        = "119--125",
)
@article(Auer02,
 author       = "Peter Auer and Nicol\`{o} Cesa-Bianchi and Paul Fischer",
 year         = "2002",
 title        = "Finite-time Analysis of the Multiarmed Bandit Problem",
 journal      = "Machine Learning",
 volume       = "27",
 pages        = "235--256",
 doi          = "10.1023/A:1013689704352",
)
@article(Bauer11,
 author       = "Tim Bauer and Martin Erwig and Alan Fern and Jervis Pinto",
 year         = "2011",
 title        = "Adaptation-Based Programming in Java",
 journal      = "PEPM '11",
 pages        = "81--90",
 doi          = "10.1145/1929501.1929518",
)
@misc(haskell-abp,
 author       = "{Bauer, Tim and Erwig, Martin and Fern, Alan and Pinto, Jervis}",
 title        = "{ABP}",
 note         = "\url {http://web.engr.oregonstate.edu/ bauertim/abp/}",
)
@book(Bishop06,
 author       = "Christopher Bishop",
 year         = "2006",
 title        = "Pattern Recognition and Machine Learning",
 publisher    = "Springer",
)
@inproceedings(Dietterich98,
 author       = "Thomas Dietterich",
 year         = "1998",
 title        = "The {MAXQ} Method for Hierarchical Reinforcement Learning",
 booktitle    = "International Conference on Machine Learning",
 pages        = "118--126",
)
@inproceedings(Lagoudakis00,
 author       = "Michail Lagoudakis and Michael Littman",
 year         = "2000",
 title        = "Algorithm Selection using Reinforcement Learning",
 booktitle    = "International Conference on Machine Learning",
 pages        = "511--518",
)
@article(Lai85,
 author       = "T. Lai and H. Robbins",
 year         = "1985",
 title        = "Asymptotically efficient adaptive allocation rules",
 journal      = "Advances in Applied Mathematics",
 volume       = "6",
 pages        = "4--22",
 doi          = "10.1109/TAC.1987.1104491",
)
@article(Lev44,
 author       = "K. Levenberg",
 year         = "1944",
 title        = "A method for the solution of certain non-linear problems in least squares",
 journal      = "Applied Math Quarterly",
 pages        = "164--168",
)
@inproceedings(Littman94,
 author       = "Michael Littman",
 year         = "1994",
 title        = "Markov Games as a Framework for Multi-Agent Reinforcement Learning",
 booktitle    = "International Conference on Machine Learning",
 pages        = "157--163",
)
@inproceedings(Maclin05,
 author       = "R. Maclin and J. Shavlik and L. Torrey and T. Walker and E. Wild",
 year         = "2005",
 title        = "Giving Advice about Preferred Actions to Reinforcement Learners Via Knowledge-Based Kernel Regression",
 booktitle    = "Proceedings of the Twentieth National Conference on Artificial Intelligence",
 pages        = "819--824",
)
@article(MAR63,
 author       = "D. Marquardt",
 year         = "1963",
 title        = "An algorithm for least-squares estimation of nonlinear parameters",
 journal      = "SIAM Journal of Applied Mathematics",
)
@techreport(UCTP,
 author       = "H. B. Nielsen",
 year         = "2000",
 title        = "UCTP - Test Problems for Unconstrained Optimization",
 type         = "Technical Report",
 institution  = "Technical University of Denmark",
)
@article(Robbins52,
 author       = "H. Robbins",
 year         = "1952",
 title        = "Some Aspects of the Sequential Design of Experiments",
 journal      = "Bulletin of the American Mathematical Society",
 volume       = "58",
 pages        = "527--535",
 doi          = "10.1090/S0002-9904-1952-09620-8",
)
@inproceedings(Ruv08,
 author       = "Paul Ruvolo and Ian R. Fasel and Javier R. Movellan",
 year         = "2008",
 title        = "Optimization on a Budget: A Reinforcement Learning Approach",
 booktitle    = "Neural Information Processing Symposium (NIPS)",
 pages        = "1385--1392",
)
@inproceedings(SPC08,
 author       = "T. Schrijvers and S. {Peyton-Jones} and M. Chakravarty",
 year         = "2008",
 title        = "{Type Checking with Open Type Functions}",
 booktitle    = "{ACM Int.\ Conf.\ on Functional Programming}",
 pages        = "51--62",
 doi          = "10.1145/1411203.1411215",
)
@inproceedings(Simpkins08,
 author       = "Christopher Simpkins and Sooraj Bhat and Michael Mateas and Charles Isbell",
 year         = "2008",
 title        = "Toward Adaptive Programming: Integrating Reinforcement Learning into a Programming Language",
 booktitle    = "ACM Conference on Object-Oriented Programming Systems, Languages and Applications",
 pages        = "603--614",
 doi          = "10.1145/1449955.1449811",
)
@book(RL-book,
 author       = "Richard Sutton and Andrew Barto",
 year         = "2000",
 title        = "Reinforcement Learning: An Introduction",
 publisher    = "MIT Press",
)
@book(Tho91,
 author       = "S. Thompson",
 year         = "1991",
 title        = "{Type Theory and Functional Programming}",
 publisher    = "{Ad\-di\-son-Wes\-ley}",
 address      = "Redwood City, CA, USA",
)