Регистрация | Вход в службу | FAQ      [?] 
Recent | Unread | Search | Authors | Tags | Export

gagliol bandit [29 articles]

Recent papers added to gagliol library classified by the tag bandit. You can also see everyone's bandit.
  • Algorithm Selection as a Bandit Problem with Unbounded Losses
    No. IDSIA - 07 - 08. (July 2008)
    by Matteo Gagliolo, Jürgen Schmidhuber
    posted to algorithm-portfolios algorithm-selection bandit dynamic non-stochastic online unbounded-losses by gagliol on 2008-08-05 19:48:33 as read along with 1 person bsilverthorn
  • The Weighted Majority Algorithm
    Inf. Comput., Vol. 108, No. 2. (1994), pp. 212-261.
    by Nick Littlestone, Manfred K Warmuth
    posted to bandit full-information online regret by gagliol on 2008-02-20 22:48:13 as **
  • Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
    Vol. 4264 (2006), pp. 229-243.
    by Chamy Allenberg, Peter Auer, László Györfi, György Ottucsák
    edited by José L Balcázar, Philip M Long, Frank Stephan, José L Balcázar, Philip M Long, Frank Stephan
    posted to bandit hannan partial-information unbounded-loss by gagliol on 2008-02-20 17:45:12 as **
  • Improved Second-Order Bounds for Prediction with Expert Advice
    Vol. 3559 (2005), pp. 217-232.
    by Nicolò C Bianchi, Yishay Mansour, Gilles Stoltz
    edited by Peter Auer, Ron Meir, Peter Auer, Ron Meir
    posted to bandit partial-information unbounded-loss by gagliol on 2008-02-20 17:42:46 as read
  • How to Beat the Adaptive Multi-Armed Bandit
    CoRR, Vol. abs/cs/0602053 (2006)
    by Varsha Dani, Thomas P Hayes
    posted to bandit printed by gagliol on 2008-02-07 14:27:10 as read
  • Robbing the bandit: less regret in online geometric optimization against an adaptive adversary
    (2006), pp. 937-943.
    by Varsha Dani, Thomas P Hayes
    posted to bandit printed by gagliol on 2008-02-07 14:24:01 as ** along with 1 person bsilverthorn
  • Potential-Based Algorithms in On-Line Prediction and Game Theory
    Machine Learning, Vol. 51, No. 3. (2003), pp. 239-261.
    by Nicolò C Bianchi, Gábor Lugosi
    posted to bandit online-learning printed by gagliol on 2008-01-29 16:27:35 as **
  • Sequential Prediction of Unbounded Stationary Time Series
    Information Theory, IEEE Transactions on, Vol. 53, No. 5. (2007), pp. 1866-1872.
    by L Gyorfi, G Ottucsak
    posted to bandit printed time-series by gagliol on 2008-01-29 16:01:00 as **
  • Improved second-order bounds for prediction with expert advice
    Machine Learning, Vol. 66, No. 2-3. (March 2007), pp. 321-352.
    by Nicolò C Bianchi, Yishay Mansour, Gilles Stoltz
    posted to bandit online-learning printed unbounded-loss by gagliol on 2008-01-17 14:53:06 as **
  • notes Learning dynamic algorithm portfolios
    Annals of Mathematics and Artificial Intelligence, Vol. 47, No. 3-4. (August 2006), pp. 295-328.
    by Matteo Gagliolo, Jürgen Schmidhuber
    posted to parallel-computing algorithm-portfolios computational-complexity algorithm-selection combinatorial-auctions combinatorial-optimization constraint-satisfaction runtime-distributions survival-analysis bandit conditional gagliolo-phd satisfiability by gagliol on 2007-12-16 11:55:24 as ** along with 1 person bsilverthorn
  • Selecting among heuristics by solving thresholded k-armed bandit problems
    (2006)
    by Matthew J Streeter, Stephen F Smith
    posted to bandit algorithm-selection max-k-armed-bandit by gagliol on 2007-12-14 15:16:34 as **
  • Combining Multiple Heuristics Online
    (2007), pp. 1197-1203.
    by Matthew J Streeter, Daniel Golovin, Stephen F Smith
    posted to bandit parallel-computing algorithm-portfolios algorithm-selection by gagliol on 2007-12-14 14:27:51 as ***
  • Restart Schedules for Ensembles of Problem Instances
    (2007), pp. 1204-1210.
    by Matthew J Streeter, Daniel Golovin, Stephen F Smith
    posted to bandit restart by gagliol on 2007-12-14 14:23:31 as **
  • Online Selection, Adaptation, and Hybridization of Algorithms
    (16 November 2006)
    by Matthew J Streeter
    posted to bandit restart parallel-computing algorithm-portfolios algorithm-selection by gagliol on 2007-12-14 14:18:19 as **
  • Q-Learning for Bandit Problems
    (1995), pp. 209-217.
    by Michael O Duff
    posted to bandit printed reinforcement-learning by gagliol on 2007-12-13 16:27:41 as ***
  • Multi-armed bandits in discrete and continuous time
    The Annals of Applied Probability, Vol. 8 (1998), pp. 1270-1290.
    by Haya Kaspi, Avishai Mandelbaum
    posted to bandit continuous-time by gagliol on 2007-03-06 13:04:55 as ***
  • Online choice of active learning algorithms
    (2003), pp. 19-26.
    by Y Baram, El R Yaniv, K Luz
    posted to bandit active-learning online-learning kernel-methods by gagliol on 2006-10-07 12:55:57 as read along with 2 people Mohan-S jread82
  • A Simple Distribution-Free Approach to the Max k-Armed Bandit Problem.
    (2006)
    by Matthew J Streeter, Stephen F Smith
    posted to bandit by gagliol on 2006-08-31 14:10:38 as **
  • Combining Expert Advice in Reactive Environments
    experts bandit exploration-exploitation (2004)
    by pucci, N Megiddo
    posted to bandit experts exploration-explotation stationary adversarial-setting reinforcement-learning by gagliol on 2006-08-22 12:44:55 as **
  • Reinforcement Learning: A Survey
    Journal of Artificial Intelligence Research, Vol. 4 (1996), pp. 237-285.
    by Leslie P Kaelbling, Michael L Littman, Andrew P Moore
    posted to bandit reinforcement-learning by gagliol on 2006-08-21 17:44:12 as read along with 20 people and 5 groups KurtSteinkraus eldan unnonouno dep vaasu cyph3r davidmihalcik craigtalbert damcci hllee lop afoerster sugarexpletive mzygmunt dowlingj josepe docB bach tdahl Tominator Glimcher_Lab Netmob P2P SensorNetworks kickOffTUG-Robocup
  • An Asymptotically Optimal Algorithm for the Max k-Armed Bandit Problem.
    (2006)
    by Matthew J Streeter, Stephen F Smith
    posted to bandit by gagliol on 2006-08-14 21:03:20 as **
  • The Max k-Armed Bandit: A New Model of Exploration Applied to Search Heuristic Selection.
    (2005), pp. 1355-1361.
    by Vincent A Cicirello, Stephen F Smith
    posted to bandit by gagliol on 2006-08-14 20:26:09 as **
  • Finite-time Analysis of the Multiarmed Bandit Problem
    Machine Learning, Vol. 47, No. 2/3. (2002), pp. 235-256.
    by Peter Auer, Nicolò C Bianchi, Paul Fischer
    posted to bandit by gagliol on 2006-08-14 19:58:43 as **
  • The Nonstochastic Multiarmed Bandit Problem
    SIAM J. Comput., Vol. 32, No. 1. (2003), pp. 48-77.
    by Peter Auer, Nicolò; C Bianchi, Yoav Freund, Robert E Schapire
    posted to bandit by gagliol on 2006-08-14 19:56:52 as ***
  • Online convex optimization in the bandit setting: gradient descent without a gradient
    (2 Aug 2004)
    by Abraham D Flaxman, Adam T Kalai, Brendan H Mcmahan
    posted to bandit convex-optimization optimization stochastic-gradient by gagliol on 2006-07-17 13:21:35 as read along with 1 person abie
  • Competitive on-line learning with a convex loss function
    (2 Sep 2005)
    by Vladimir Vovk
    posted to bandit by gagliol on 2006-07-17 11:32:33 as **** along with 1 person davidr
  • Bandit Problems: Sequential Allocation of Experiments
    (1985)
    by DA Berry, B Fristedt
    posted to bandit by gagliol on 2006-07-17 11:24:54 as **
  • Reinforcement learning: An introduction
    (1998)
    by R Sutton, A Barto
    posted to bandit reinforcement-learning by gagliol on 2006-07-17 11:24:54 as **
  • Gambling in a rigged casino: the adversarial multi-armed bandit problem
    (1995), pp. 322-331.
    by Peter Auer, Nicolò C Bianchi, Yoav Freund, Robert E Schapire
    posted to bandit adversarial-setting by gagliol on 2006-07-17 11:24:53 as read along with 2 people and 2 groups camu Scis0000002 Crypto Randomness
    • Вы можете ссылаться на эту страницу по адресу: http://www.citeulike.org/user/gagliol/tag/bandit

    RIS BibTeX
    CiteULike organises scholarly (or academic) papers or literature and provides bibliographic (which means it makes bibliographies) for universities and higher education establishments. It helps undergraduates and postgraduates. People studying for PhDs or in postdoctoral (postdoc) positions. The service is similar in scope to EndNote or RefWorks or any other reference manager like BibTeX, but it is a social bookmarking service for scientists and humanities researchers.