Search dblp for Publications

export results for "toc:db/journals/ml/ml49.bht:"

 download as .bib file

@article{DBLP:journals/ml/Boyan02,
  author       = {Justin A. Boyan},
  title        = {Technical Update: Least-Squares Temporal Difference Learning},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {233--246},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017936530646},
  doi          = {10.1023/A:1017936530646},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/Boyan02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/Dahl02,
  author       = {Fredrik A. Dahl},
  title        = {The Lagging Anchor Algorithm: Reinforcement Learning in Two-Player
                  Zero-Sum Games with Imperfect Information},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {1},
  pages        = {5--37},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1014063505958},
  doi          = {10.1023/A:1014063505958},
  timestamp    = {Fri, 09 Apr 2021 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ml/Dahl02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/FosterD02,
  author       = {David J. Foster and
                  Peter Dayan},
  title        = {Structure in the Space of Value Functions},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {325--346},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017944732463},
  doi          = {10.1023/A:1017944732463},
  timestamp    = {Fri, 27 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/FosterD02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/KearnsMN02,
  author       = {Michael J. Kearns and
                  Yishay Mansour and
                  Andrew Y. Ng},
  title        = {A Sparse Sampling Algorithm for Near-Optimal Planning in Large Markov
                  Decision Processes},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {193--208},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017932429737},
  doi          = {10.1023/A:1017932429737},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/KearnsMN02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/KearnsS02,
  author       = {Michael J. Kearns and
                  Satinder Singh},
  title        = {Near-Optimal Reinforcement Learning in Polynomial Time},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {209--232},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017984413808},
  doi          = {10.1023/A:1017984413808},
  timestamp    = {Tue, 19 Apr 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ml/KearnsS02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/Lee02,
  author       = {Michael D. Lee},
  title        = {A Simple Method for Generating Additive Clustering Models with Limited
                  Complexity},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {1},
  pages        = {39--58},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1014112506867},
  doi          = {10.1023/A:1014112506867},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/Lee02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/MarkovitchR02,
  author       = {Shaul Markovitch and
                  Dan Rosenstein},
  title        = {Feature Generation Using General Constructor Functions},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {1},
  pages        = {59--98},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1014046307775},
  doi          = {10.1023/A:1014046307775},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/MarkovitchR02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/McGovernMB02,
  author       = {Amy McGovern and
                  J. Eliot B. Moss and
                  Andrew G. Barto},
  title        = {Building a Basic Block Instruction Scheduler with Reinforcement Learning
                  and Rollouts},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {141--160},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017976211990},
  doi          = {10.1023/A:1017976211990},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/McGovernMB02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/MihatschN02,
  author       = {Oliver Mihatsch and
                  Ralph Neuneier},
  title        = {Risk-Sensitive Reinforcement Learning},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {267--290},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017940631555},
  doi          = {10.1023/A:1017940631555},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/MihatschN02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/MillanPD02,
  author       = {Jos{\'{e}} del R. Mill{\'{a}}n and
                  Daniele Posenato and
                  Eric Dedieu},
  title        = {Continuous-Action Q-Learning},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {247--265},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017988514716},
  doi          = {10.1023/A:1017988514716},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/MillanPD02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/MunosM02,
  author       = {R{\'{e}}mi Munos and
                  Andrew W. Moore},
  title        = {Variable Resolution Discretization in Optimal Control},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {291--323},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017992615625},
  doi          = {10.1023/A:1017992615625},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/MunosM02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/OrmoneitS02,
  author       = {Dirk Ormoneit and
                  Saunak Sen},
  title        = {Kernel-Based Reinforcement Learning},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {161--178},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017928328829},
  doi          = {10.1023/A:1017928328829},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/OrmoneitS02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/Singh02,
  author       = {Satinder Singh},
  title        = {Introduction},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {107--109},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017917511082},
  doi          = {10.1023/A:1017917511082},
  timestamp    = {Tue, 19 Apr 2022 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/ml/Singh02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/TongB02,
  author       = {Hui Tong and
                  Timothy X. Brown},
  title        = {Reinforcement Learning for Call Admission Control and Routing under
                  Quality of Service Constraints in Multimedia Networks},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {111--139},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017924227920},
  doi          = {10.1023/A:1017924227920},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/TongB02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

@article{DBLP:journals/ml/TsitsiklisR02,
  author       = {John N. Tsitsiklis and
                  Benjamin Van Roy},
  title        = {On Average Versus Discounted Reward Temporal-Difference Learning},
  journal      = {Mach. Learn.},
  volume       = {49},
  number       = {2-3},
  pages        = {179--191},
  year         = {2002},
  url          = {https://doi.org/10.1023/A:1017980312899},
  doi          = {10.1023/A:1017980312899},
  timestamp    = {Mon, 02 Mar 2020 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ml/TsitsiklisR02.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.