, Pour permettre la visualisation, on s'intéresse à la coordonnée y de p f in en fonction de q 0,0 (la première coordonnée de q 0 ) et q 1,0 (la première coordonnée de q 1 ). Les points verts sont prédits par un expert associé sur y à une fonction de P 3,{q 1,0 } (complexité 4), les points oranges par un expert associé sur y à une fonction de P 2,{q 1,0 } (complexité 3), les points rouges par un expert associé sur y à une fonction de P 0, Expérience : simulation d'interaction d'un bras robotique avec un cube Figure 5.13-À l'issue de l'apprentissage, COCOTTE rend compte du jeu d'entraînement à l'aide de 4 experts

N. S. Altman, An introduction to kernel and nearest-neighbor nonparametric regression, The American Statistician, vol.46, issue.3, pp.175-185, 1992.

T. Bansal, . Pachocki, . Jakub, . Sidor, . Szymon et al., Emergent complexity via multi-agent competition, 2017.

O. Beijbom, Domain adaptations for computer vision applications. CoRR, abs/1211, vol.4860, 2012.

G. Bradski, The opencv library. Dr. Dobb's Journal : Software Tools for the Professional Programmer, vol.25, pp.120-123, 2000.

L. Breiman, Random forests. Machine learning, vol.45, pp.5-32, 2001.

W. S. Cleveland and S. J. Devlin, Locally weighted regression : an approach to regression analysis by local fitting, Journal of the American statistical association, vol.83, issue.403, pp.596-610, 1988.

B. Da-silva, . Castro, G. Konidaris, and A. G. Barto, Learning parameterized skills, Proceedings of the 29th International Conference on Machine Learning, ICML 2012, 2012.

W. Dai, . Yang, . Qiang, G. Xue, and Y. Yu, Boosting for transfer learning, Machine Learning, Proceedings of the Twenty-Fourth International Conference (ICML 2007), pp.193-200, 2007.

C. Devin, . Gupta, . Abhishek, . Darrell, . Trevor et al., Learning modular neural network policies for multi-task and multi-robot transfer, 2016.

M. Dredze, A. Kulesza, . Et-crammer, and . Koby, Multi-domain learning by confidence-weighted parameter combination, Machine Learning, vol.79, pp.123-149, 2010.

H. Drucker, . Burges, J. C. Christopher, . Kaufman, . Linda et al., Support vector regression machines, Advances in neural information processing systems, pp.155-161, 1997.

P. Ecarlat, A. Cully, C. Maestre, and S. Doncieux, Learning a high diversity of object manipulations though an evolutionary-based babbling, Proceedings of the workshop Learning Object Affordances, pp.1-2, 2015.

B. Efron, . Hastie, . Trevor, I. Johnstone, and R. Tibshirani, Least angle regression, Ann. Statist, vol.32, issue.2, pp.407-499, 2004.

T. Evgeniou and M. Pontil, Regularized multitask learning, Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.109-117, 2004.

R. M. French, Catastrophic forgetting in connectionist networks, Trends in cognitive sciences, vol.3, issue.4, pp.128-135, 1999.

Y. Freund and R. E. Schapire, A decision-theoretic generalization of on-line learning and an application to boosting, J. Comput. Syst. Sci, vol.55, issue.1, pp.119-139, 1997.

P. Geladi, . Kowalski, and R. Bruce, Partial least-squares regression : a tutorial, Analytica chimica acta, vol.185, pp.1-17, 1986.

J. D. Gergonne, The application of the method of least squares to the interpolation of sequences, Historia Mathematica, vol.1, issue.4, pp.439-447, 1974.

A. Ghadirzadeh, J. Bütepage, D. Kragic, and M. Et-björkman, Self-learning and adaptation in a sensorimotor framework, IEEE, pp.551-558, 2016.

I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, 2016.

J. Hoffman, T. Darrell, and K. Saenko, Continuous manifold based adaptation for evolving visual domains, IEEE Conference on Computer Vision and Pattern Recognition, pp.867-874, 2014.

R. A. Jacobs, M. I. Jordan, . Nowlan, J. Steven, and G. E. Et-hinton, Adaptive mixtures of local experts, Neural Computation, vol.3, issue.1, pp.79-87, 1991.

. Kim, . Sanghong, . Kano, . Manabu, H. Nakagawa et al., Estimation of active pharmaceutical ingredients content using locally weighted partial least squares and statistical wavelength selection. International journal of pharmaceutics, vol.421, pp.269-274, 2011.

J. Kirkpatrick, . Pascanu, . Razvan, . Rabinowitz, . Neil et al., Overcoming catastrophic forgetting in neural networks, Proceedings of the National Academy of Sciences, p.201611835, 2017.

J. Kober, A. Wilhelm, . Oztop, . Erhan, and . Peters, Reinforcement learning to adjust parametrized motor primitives to new situations, Auton. Robots, vol.33, issue.4, pp.361-379, 2012.

V. Kompella, . Raj, . Stollenga, F. Marijn, M. D. Luciw et al., Explore to see, learn to perceive, get the actions for free : SKILLABILITY, International Joint Conference on Neural Networks, pp.2705-2712, 2014.

G. D. Konidaris, S. R. Kuindersma, R. A. Grupen, and A. G. Barto, Cst : Constructing skill trees by demonstration, Proceedings of the ICML Workshop on New Developments in Imitation Learning, 2011.

D. Kulic, . Ott, . Christian, . Lee, . Dongheui et al., Incremental learning of full body motion primitives and their sequencing through human motion observation, I. J. Robotics Res, vol.31, issue.3, pp.330-345, 2012.

A. Kumar, H. Iii, and . Daumé, Learning task grouping and overlap in multi-task learning, Proceedings of the 29th International Conference on Machine Learning, ICML 2012, 2012.

N. D. Lawrence and J. C. Platt, Learning to learn with the informative vector machine, Machine Learning, Proceedings of the Twentyfirst International Conference (ICML 2004), 2004.

M. Lázaro-gredilla, V. Vaerenbergh, . Steven, . Lawrence, and D. Neil, Overlapping mixtures of gaussian processes for the data association problem, Pattern Recognition, vol.45, issue.4, pp.1386-1395, 2012.

A. Lemme, R. Reinhart, . Felix, J. Steil, and . Jakob, Selfsupervised bootstrapping of a movement primitive library from complex trajectories, 14th IEEE-RAS International Conference on Humanoid Robots, Humanoids, pp.726-732, 2014.

A. Matricon, D. Filliat, and P. Oudeyer, An iterative algorithm for forward-parameterized skill discovery, Joint IEEE International Conference on Development and Learning and Epigenetic Robotics, ICDL-EpiRob, pp.186-192, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01370820

. Mihalkova, . Lilyana, . Huynh, N. Tuyen, and R. J. Mooney, Mapping and revising markov logic networks for transfer learning, Proceedings of the Twenty-Second AAAI Conference on Artificial Intelligence, pp.608-614, 2007.

C. Moulin-frier and P. Oudeyer, Learning how to reach various goals by autonomous interaction with the environment : unification and comparison of exploration strategies, 1st Multidisciplinary Conference on Reinforcement Learning and Decision Making (RLDM2013), 2014.
URL : https://hal.archives-ouvertes.fr/hal-00922537

P. Oudeyer, . Kaplan, . Frédéric, V. Hafner, and . Vanessa, Intrinsic motivation systems for autonomous mental development, IEEE Trans. Evolutionary Computation, vol.11, issue.2, pp.265-286, 2007.

S. Pan, . Jialin, . Yang, and . Qiang, A survey on transfer learning, IEEE Trans. Knowl. Data Eng, vol.22, issue.10, pp.1345-1359, 2010.

. Pastor, . Peter, . Hoffmann, . Heiko, . Asfour et al., Learning and generalization of motor skills by learning from demonstration, IEEE, pp.763-768, 2009.

J. Peters and S. Schaal, Reinforcement learning of motor skills with policy gradients, Neural Networks, vol.21, issue.4, pp.682-697, 2008.

R. Raina, A. Battle, . Lee, . Honglak, . Packer et al., Self-taught learning : transfer learning from unlabeled data, Machine Learning, Proceedings of the Twenty-Fourth International Conference (ICML 2007), pp.759-766, 2007.

M. Rolf, . Steil, and J. Jochen, Goal Babbling : a New Concept for Early Sensorimotor Exploration, 2012.

M. T. Rosenstein, . Marx, . Zvika, L. Kaelbling, . Pack et al., To transfer or not to transfer, NIPS'05, 2005.

I. Workshop and . Transfer,

S. Schaal, . Atkeson, and G. Christopher, Robot juggling : implementation of memory-based learning, IEEE Control Systems, vol.14, issue.1, pp.57-71, 1994.

S. Schaal, . Atkeson, and G. Christopher, Receptive field weighted regression. ATR Human Information Processing Laboratories, 1997.

C. E. Shannon, Coding theorems for a discrete source with a fidelity criterion, IRE Nat. Conv. Rec, p.1, 1959.

. Sigaud, . Olivier, C. Salaün, and V. Padois, On-line regression algorithms for learning mechanical models of robots : A survey, Robotics and Autonomous Systems, vol.59, issue.12, pp.1115-1129, 2011.
URL : https://hal.archives-ouvertes.fr/hal-00629133

A. J. Smola and B. Et-schölkopf, A tutorial on support vector regression, Statistics and Computing, vol.14, issue.3, pp.199-222, 2004.

M. Stolle and D. Precup, Learning options in reinforcement learning, Reformulation and Approximation, 5th International Symposium, pp.212-223, 2002.

. Stulp, . Freek, . Herlant, . Laura, A. Hoarau et al., Simultaneous on-line discovery and improvement of robotic skill options, RSJ International Conference on Intelligent Robots and Systems, pp.1408-1413, 2014.
URL : https://hal.archives-ouvertes.fr/hal-01089097

F. Stulp and O. Sigaud, Many regression algorithms, one unified model : A review, Neural Networks, vol.69, pp.60-79, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01162281

. Sun, . Shiliang, . Shi, . Honglei, and Y. Wu, A survey of multi-source domain adaptation. Information Fusion, vol.24, pp.84-92, 2015.

R. S. Sutton, . Precup, . Doina, . Singh, and P. Satinder, Between MDPs and semi-MDPs : A framework for temporal abstraction in reinforcement learning, Artif. Intell, vol.112, issue.1-2, pp.52-53, 1999.

M. E. Taylor, . Stone, . Peter, and Y. Liu, Value functions for rl-based behavior transfer : A comparative study, The Twentieth National Conference on Artificial Intelligence and the Seventeenth Innovative Applications of Artificial Intelligence Conference, pp.880-885, 2005.

J. B. Tenenbaum, D. Silva, V. Langford, and C. John, A global geometric framework for nonlinear dimensionality reduction, science, vol.290, issue.5500, pp.2319-2323, 2000.

V. N. Vapnik, The nature of statistical learning theory, 1999.

S. Vijayakumar and S. Schaal, Locally weighted projection regression : Incremental real time learning in high dimensional space, Proceedings of the Seventeenth International Conference on Machine Learning (ICML 2000), pp.1079-1086, 2000.

. Wold, . Svante, K. Esbensen, and P. Geladi, Principal component analysis. Chemometrics and intelligent laboratory systems, vol.2, pp.37-52, 1987.

D. M. Wolpert and M. Et-kawato, Multiple paired forward and inverse models for motor control, Neural Networks, vol.11, issue.7-8, pp.66-71, 1998.

R. Wunderling, Soplex : The sequential object-oriented simplex class library, 1997.

Y. Yang and T. M. Hospedales, A unified perspective on multi-domain and multi-task learning, 2014.