Bibliography

Publications of the year

Doctoral Dissertations and Habilitation Theses

1A. Carpentier.

Toward optimal sampling in low and high dimension, Université Lille 1, Lille, France, Octobre 2012.
2E. Delande.

Multi-sensor PHD filtering with application to sensor management, Ecole Centrale, Lille, France, Octobre 2012.

http://www.theses.fr/2012ECLI0001
3J. F. Hren.

Planification optimiste pour systèmes dèterministes, Université Lille 1, Lille, France, Juin 2012.
4C. Salperwyck.

Apprentissage incrémental en ligne sur flux de données, Université de Lille 3, Nov 2012.

Articles in International Peer-Reviewed Journals

5M. G. Azar, R. Munos, H. Kappen.

Minimax PAC-Bounds on the Sample Complexity of Reinforcement Learning with a Generative Model, in: Machine Learning Journal, 2012, To appear.
6O. Cappé, A. Garivier, O.-A. Maillard, R. Munos, G. Stoltz.

Kullback-Leibler Upper Confidence Bounds for Optimal Sequential Allocation, in: Annals of Statistics, 2012, Submitted to.
7A. Carpentier, A. Lazaric, M. Ghavamzadeh, R. Munos, P. Auer.

Upper-Confidence-Bound Algorithms for Active Learning in Multi-Armed Bandits, in: Theoretical Computer Science, 2012, To appear.
8A. Carpentier, R. Munos, A. Antos.

Minimax strategy for Stratified Sampling for Monte Carlo, in: Journal of Machine Learning Research, 2012, Submitted to.
9G. Dulac-Arnold, L. Denoyer, P. Preux, P. Gallinari.

Sequential approaches for learning datum-wise sparse representations, in: Machine Learning, October 2012, vol. 89, n^o 1-2, p. 87-122.
10J. Fruitet, A. Carpentier, R. Munos, M. Clerc.

Automatic motor task selection via a bandit algorithm for a brain-controlled button, in: Journal of Neural Engineering, 2012, To appear.
11S. Girgin, J. Mary, P. Preux, O. Nicol.

Managing advertising campaigns – an approximate planning approach, in: Frontiers of Computer Science, 2012, vol. 6, n^o 2, p. 209-229. [ DOI : 10.1007/s11704-012-2873-5 ]

http://hal.inria.fr/hal-00747722
12M. Hauskrecht, I. Batal, M. Valko, S. Visweswaran, G. F. Cooper, G. Clermont.

Outlier detection for patient monitoring and alerting., in: Journal of Biomedical Informatics, August 2012. [ DOI : 10.1016/j.jbi.2012.08.004 ]

http://hal.inria.fr/hal-00742097
13A. Lazaric, M. Ghavamzadeh, R. Munos.

Analysis of Classification-based Policy Iteration Algorithms, in: Journal of Machine learning Research, 2012, Submitted to.
14A. Lazaric, M. Ghavamzadeh, R. Munos.

Finite-Sample Analysis of Least-Squares Policy Iteration, in: Journal of Machine Learning Research, 2012, vol. 13, p. 3041-3074.
15A. Lazaric, R. Munos.

Learning with stochastic inputs and adversarial outputs, in: Journal of Computer and System Sciences (JCSS), 2012, vol. 78, n^o 5, p. 1516–1537. [ DOI : 10.1016/j.jcss.2011.12.027 ]

http://www.sciencedirect.com/science/article/pii/S002200001200027X
16O.-A. Maillard, R. Munos.

Linear Regression with Random Projections, in: Journal of Machine learning Research, 2012, vol. 13, p. 2735-2772.
17R. Munos.

The Optimistic Principle applied to Games, Optimization and Planning: Towards Foundations of Monte-Carlo Tree Search, in: Foundations and Trends in Machine Learning, 2012, Submitted to.

http://hal.archives-ouvertes.fr/hal-00747575
18O. Nicol, J. Mary, P. Preux.

ICML Exploration & Exploitation challenge: Keep it simple!, in: Journal of Machine Learning research Workshop and Conference Proceedings, 2012, vol. 26, p. 62-85.

http://hal.inria.fr/hal-00747725
19A. Rabaoui, N. Viandier, J. Marais, E. Duflos, P. Vanheeghe.

Dirichlet Process Mixtures for Density Estimation in Dynamic Nonlinear Modeling: Application to GPS Positioning in Urban Canyons, in: IEEE Transactions on Signal Processing, April 2012, vol. 60, n^o 4, p. 1638 - 1655. [ DOI : 10.1109/TSP.2011.2180901 ]

http://hal.inria.fr/hal-00712718
20S. Razavi, E. Duflos, C. Haas, P. Vanheeghe.

Dislocation detection in field environments: A belief functions contribution, in: Expert Systems with Applications, August 2012, vol. 39, n^o 10, p. 8505-8513. [ DOI : 10.1016/j.eswa.2011.12.014 ]

http://hal.inria.fr/hal-00712720
21D. Ryabko.

Testing composite hypotheses about discrete ergodic processes, in: Test, 2012, vol. 21, n^o 2, p. 317-329.
22D. Ryabko.

Uniform hypothesis testing for finite-valued stationary processes, in: Statistics, 2013.
23M. Valko, M. Ghavamzadeh, A. Lazaric.

Semi-Supervised Apprenticeship Learning, in: Journal of Machine Learning Research: Workshop and Conference Proceedings, November 2012, vol. 24.

http://hal.inria.fr/hal-00747921

International Conferences with Proceedings

24M. G. Azar, R. Munos, H. Kappen.

On the Sample Complexity of Reinforcement Learning with a Generative Model, in: International Conference on Machine Learning, 2012.
25L. Busoniu, R. Munos.

Optimistic planning in Markov decision processes, in: International conference on Artificial Intelligence and Statistics, 2012.
26A. Carpentier, R. Munos.

Adaptive Stratified Sampling for Monte-Carlo integration of Differentiable functions, in: Advances in Neural Information Processing Systems, 2012.
27A. Carpentier, R. Munos.

Bandit Theory meets Compressed Senseing for high dimensional Stochastic Linear Bandit, in: International conference on Artificial Intelligence and Statistics, 2012.
28A. Carpentier, R. Munos.

Minimax number of strata for online Stratified Sampling given Noisy Samples, in: International Conference on Algorithmic Learning Theory, 2012.
29P. Chainais.

Towards dictionary learning from images with non Gaussian noise, in: IEEE Int. Workshop on Machine Learning for Signal Processing, Santander, Spain, September 2012, 0000 p.

http://hal.inria.fr/hal-00749035
30R. Coulom.

CLOP: Confident Local Optimization for Noisy Black-Box Parameter Tuning, in: Advances in Computer Games - 13th International Conference, Tilburg, Pays-Bas, H. J. van den Herik, A. Plaat (editors), Lecture Notes in Computer Science, Springer, 2012, vol. 7168, p. 146-157. [ DOI : 10.1007/978-3-642-31866-5_13 ]

http://hal.inria.fr/hal-00750326
31G. Dulac-Arnold, L. Denoyer, P. Preux, P. Gallinari.

Fast Reinforcement Learning with Large Action Sets Using Error-Correcting Output Codes for MDP Factorization, in: European Conference on Machine Learning, Bristol, United Kingdom, Springer, 2012, vol. 2, p. 180-194. [ DOI : 10.1007/978-3-642-33486-3_12 ]

http://hal.inria.fr/hal-00747729
32J. Fruitet, A. Carpentier, R. Munos, M. Clerc.

Bandit Algorithms boost motor-task selection for Brain Computer Interfaces, in: Advances in Neural Information Processing Systems, 2012.
33V. Gabillon, M. Ghavamzadeh, A. Lazaric.

Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence, in: Proceedings of Advances in Neural Information Processing Systems 25, MIT Press, 2012.
34N. Gatti, A. Lazaric, F. Trovò.

A Truthful Learning Mechanism for Multi-Slot Sponsored Search Auctions with Externalities (Extended Abstract), in: AAMAS, 2012.
35N. Gatti, A. Lazaric, F. Trovò.

A Truthful Learning Mechanism for Multi-Slot Sponsored Search Auctions with Externalities, in: Proceedings of the 13th ACM Conference on Electronic Commerce (EC'12), 2012.
36M. Geist, B. Scherrer, A. Lazaric, M. Ghavamzadeh.

A Dantzig Selector Approach to Temporal Difference Learning, in: Proceedings of the Twenty-Ninth International Conference on Machine Learning, 2012, p. 1399-1406.
37M. Ghavamzadeh, A. Lazaric.

Conservative and Greedy Approaches to Classification-based Policy Iteration, in: Proceedings of the Twenty-Sixth Conference on Artificial Intelligence, 2012, p. 914-920.
38E. Kauffmann, N. Korda, R. Munos.

Thompson Sampling: an Asymptotically Optimal Finite Time Analysis, in: International Conference on Algorithmic Learning Theory, 2012.
39A. Khaleghi, D. Ryabko.

Locating Changes in Highly Dependent Data with Unknown Number of Change Points, in: NIPS, Lake Tahoe, USA, 2012.
40A. Khaleghi, D. Ryabko, J. Mary, P. Preux.

Online Clustering of Processes, in: AISTATS, JMLR W&CP 22, 2012, p. 601-609.
41B. Kveton, M. Valko.

Learning from a Single Labeled Face and a Stream of Unlabeled Data, in: 10th IEEE International Conference on Automatic Face and Gesture Recognition, Shanghai, China, November 2012.

http://hal.inria.fr/hal-00749197
42O.-A. Maillard, A. Carpentier.

Online allocation and homogeneous partitioning for piecewise constant mean approximation, in: Advances in Neural Information Processing Systems, 2012.
43R. Ortner, D. Ryabko, P. Auer, R. Munos.

Regret Bounds for Restless Markov Bandits, in: Proc. 23th International Conf. on Algorithmic Learning Theory (ALT'12), Lyon, France, LNCS 7568, Springer, Berlin, 2012, p. 214–228.
44R. Ortner, D. Ryabko.

Online Regret Bounds for Undiscounted Continuous Reinforcement Learning, in: NIPS, Lake Tahoe, USA, 2012.
45D. Ryabko, J. Mary.

Reducing statistical time-series problems to binary classification, in: NIPS, Lake Tahoe, USA, 2012.
46A. Sani, A. Lazaric, R. Munos.

Risk-Aversion in Multi-Armed Bandits, in: Advances in Neural Information Processing Systems, 2012.
47B. Scherrer, M. Ghavamzadeh, V. Gabillon, M. Geist.

Approximate Modified Policy Iteration, in: Proceedings of the Twenty-Ninth International Conference on Machine Learning, 2012, p. 1207-1214.

National Conferences with Proceeding

48G. Dulac-Arnold, L. Denoyer, P. Preux, P. Gallinari.

Apprentissage par renforcement rapide pour des grands ensembles d'actions en utilisant des codes correcteurs d'erreur, in: Journées Francophones sur la planification, la décision et l'apprentissage pour le contrôle des systèmes - JFPDA 2012, Villers-lès-Nancy, France, O. Buffet (editor), 2012, 12 p p.

http://hal.inria.fr/hal-00736322
49M. Geist, B. Scherrer, A. Lazaric, M. Ghavamzadeh.

Un sélecteur de Dantzig pour l'apprentissage par différences temporelles, in: Journées Francophones sur la planification, la décision et l'apprentissage pour le contrôle des systèmes - JFPDA 2012, Villers-lès-Nancy, France, O. Buffet (editor), 2012, 13 p p.

http://hal.inria.fr/hal-00736229
50N. Jaoua, E. Duflos, P. Vanheeghe.

DPM pour l'inférence dans les modèles dynamiques non linéaires avec des bruits de mesure alpha-stable, in: 44ème Journées de Statistique, Bruxelles, Belgium, May 2012, p. 1-4.

http://hal.inria.fr/hal-00713857
51B. Scherrer, V. Gabillon, M. Ghavamzadeh, M. Geist.

Approximations de l'Algorithme Itérations sur les Politiques Modifié, in: Journées Francophones sur la planification, la décision et l'apprentissage pour le contrôle des systèmes - JFPDA 2012, Villers-lès-Nancy, France, O. Buffet (editor), 2012, 1 p p, Le corps de cet article est paru, en langue anglaise, dans ICML'2012 (Proceedings of the International Conference on Machine Learning).

http://hal.inria.fr/hal-00736226

Conferences without Proceedings

52C. Dhanjal, R. Gaudel, S. Clémençon.

Incremental Spectral Clustering with the Normalised Laplacian, in: DISCML - 3rd NIPS Workshop on Discrete Optimization in Machine Learning - 2011, Sierra Nevada, Espagne, 2012.

http://hal.inria.fr/hal-00745666
53A. Farahmand, D. Precup, M. Ghavamzadeh.

On Classification-based Approximate Policy Iteration, in: Thirtieth International Conference on Machine Learning, 2012, submitted.
54D. Ryabko.

Asymptotic statistics of stationary ergodic time series, in: WITMSE, Amsterdam, 2012.

Scientific Books (or Scientific Book chapters)

55L. Busoniu, A. Lazaric, M. Ghavamzadeh, R. Munos, R. Babuska, B. De Schutter.

Least-Squares Methods for Policy Iteration, in: Reinforcement Learning: State of the Art, M. Wiering, M. van Otterlo (editors), Springer Verlag, 2012, p. 75-110.
56A. Lazaric.

Transfer in Reinforcement Learning: a Framework and a Survey, in: Reinforcement Learning: State of the Art, M. Wiering, M. van Otterlo (editors), Springer, 2012.
57N. Vlassis, M. Ghavamzadeh, S. Mannor, P. Poupart.

Bayesian Reinforcement Learning, in: Reinforcement Learning: State of the Art, M. Wiering, M. van Otterlo (editors), Springer Verlag, 2012, p. 359-386.

Internal Reports

58V. Gabillon, M. Ghavamzadeh, A. Lazaric.

Best Arm Identification: A Unified Approach to Fixed Budget and Fixed Confidence, Inria, 2012, n^o inria-00747005.
59H. Kadri, M. Ghavamzadeh, P. Preux.

A Generalized Kernel Approach to Structured Output Learning, Inria, May 2012, n^o RR-7956.

http://hal.inria.fr/hal-00695631
60H. Kadri, A. Rakotomamonjy, F. Bach, P. Preux.

Multiple Operator-valued Kernel Learning, Inria, March 2012, n^o RR-7900.

http://hal.inria.fr/hal-00677012
61B. Pires, M. Ghavamzadeh, Cs. Szepesváari.

Risk Bounds in Cost-sensitive Multiclass Classification: an Application to Reinforcement Learning, Inria, 2012, in preparation.
62B. Scherrer, V. Gabillon, M. Ghavamzadeh, M. Geist.

Approximate Modified Policy Iteration, Inria, May 2012.

http://hal.inria.fr/hal-00697169

References in notes

63P. Auer, N. Cesa-Bianchi, P. Fischer.

Finite-time analysis of the multi-armed bandit problem, in: Machine Learning, 2002, vol. 47, n^o 2/3, p. 235–256.
64R. Bellman.

Dynamic Programming, Princeton University Press, 1957.
65D. Bertsekas, S. Shreve.

Stochastic Optimal Control (The Discrete Time Case), Academic Press, New York, 1978.
66D. Bertsekas, J. Tsitsiklis.

Neuro-Dynamic Programming, Athena Scientific, 1996.
67T. Ferguson.

A Bayesian Analysis of Some Nonparametric Problems, in: The Annals of Statistics, 1973, vol. 1, n^o 2, p. 209–230.
68T. Hastie, R. Tibshirani, J. Friedman.

The elements of statistical learning — Data Mining, Inference, and Prediction, Springer, 2001.
69W. Powell.

Approximate Dynamic Programming, Wiley, 2007.
70M. Puterman.

Markov Decision Processes: Discrete Stochastic Dynamic Programming, John Wiley and Sons, 1994.
71H. Robbins.

Some aspects of the sequential design of experiments, in: Bull. Amer. Math. Soc., 1952, vol. 55, p. 527–535.
72J. Rust.

How Social Security and Medicare Affect Retirement Behavior in a World of Incomplete Market, in: Econometrica, July 1997, vol. 65, n^o 4, p. 781–831.

http://gemini.econ.umd.edu/jrust/research/rustphelan.pdf
73J. Rust.

On the Optimal Lifetime of Nuclear Power Plants, in: Journal of Business & Economic Statistics, 1997, vol. 15, n^o 2, p. 195–208.
74R. Sutton, A. Barto.

Reinforcement learning: an introduction, MIT Press, 1998.
75G. Tesauro.

Temporal Difference Learning and TD-Gammon, in: Communications of the ACM, March 1995, vol. 38, n^o 3.

http://www.research.ibm.com/massive/tdl.html
76P. Werbos.

ADP: Goals, Opportunities and Principles, IEEE Press, 2004, p. 3–44, Handbook of learning and approximate dynamic programming.

Previous |

Home