G. Baldassarre and M. Mirolli, Intrinsically Motivated Learning in Natural and Artificial Systems, vol.9783642323, 2013.
DOI : 10.1007/978-3-642-32375-1_1

A. Cangelosi and M. Schlesinger, From Babies to Robots: The Contribution of Developmental Robotics to Developmental Psychology, Child Development Perspectives, 2018.

A. Baranes and P. Y. Oudeyer, Active learning of inverse models with intrinsically motivated goal exploration in robots, Robotics and Autonomous Systems, vol.61, issue.1, pp.49-73, 2013.
URL : https://hal.archives-ouvertes.fr/hal-00788440

B. D. Silva, G. Konidaris, and A. Barto, Active learning of parameterized skills, International Conference on Machine Learning, pp.1737-1745, 2014.

T. Hester and P. Stone, Intrinsically motivated model learning for developing curious robots, Artificial Intelligence, vol.247, pp.170-186, 2017.
DOI : 10.1016/j.artint.2015.05.002

E. Conti, V. Madhavan, F. P. Such, J. Lehman, K. O. Stanley et al., Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents, 2017.

C. Colas, O. Sigaud, and P. Oudeyer, GEP-PG: Decoupling exploration and exploitation in deep reinforcement learning, International Conference on Machine Learning (ICML), 2018.
URL : https://hal.archives-ouvertes.fr/hal-01840576

A. Cully, J. Clune, D. Tarapore, and J. Mouret, Robots that can adapt like animals, Nature, vol.521, issue.7553, p.503, 2015.
DOI : 10.1038/nature14422
URL : https://hal.archives-ouvertes.fr/hal-01158243

B. D. Argall, S. Chernova, M. Veloso, and B. Browning, A survey of robot learning from demonstration, Robotics and autonomous systems, vol.57, issue.5, pp.469-483, 2009.

P. Oudeyer, Computational theories of curiosity-driven learning, The New Science of Curiosity. NOVA, 2018.
DOI : 10.31234/osf.io/3p8f6
URL : http://arxiv.org/pdf/1802.10546

D. E. Berlyne, Curiosity and exploration, Science, vol.153, issue.3731, pp.25-33, 1966.

M. Bellemare, S. Srinivasan, G. Ostrovski, T. Schaul, D. Saxton et al., Unifying count-based exploration and intrinsic motivation, Advances in Neural Information Processing Systems, pp.1471-1479, 2016.

M. C. Machado, M. G. Bellemare, and M. Bowling, A laplacian framework for option discovery in reinforcement learning, International Conference on Machine Learning, 2017.

A. G. Barto, Intrinsic motivation and reinforcement learning, Intrinsically motivated learning in natural and artificial systems, pp.17-47, 2013.
DOI : 10.1007/978-3-642-32375-1_2

D. Pathak, P. Agrawal, A. A. Efros, and T. Darrell, Curiosity-driven exploration by selfsupervised prediction, 2017.
DOI : 10.1109/cvprw.2017.70
URL : http://arxiv.org/pdf/1705.05363

R. Houthooft, X. Chen, Y. Duan, J. Schulman, F. De-turck et al., Curiosity-driven exploration in deep reinforcement learning via bayesian neural networks, 2016.

H. Tang, R. Houthooft, D. Foote, A. Stooke, X. Chen et al., # exploration: A study of count-based exploration for deep reinforcement learning, 2016.

S. Forestier, Y. Mollard, and P. Oudeyer, Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning
URL : https://hal.archives-ouvertes.fr/hal-01651233

M. Rolf, J. J. Steil, and M. Gienger, Goal babbling permits direct learning of inverse kinematics, IEEE Transactions on Autonomous Mental Development, vol.2, issue.3, pp.216-229, 2010.

S. M. Nguyen and P. Oudeyer, Socially guided intrinsic motivation for robot learning of motor skills, Autonomous Robots, vol.36, issue.3, pp.273-294, 2014.
DOI : 10.1007/s10514-013-9339-y
URL : https://hal.archives-ouvertes.fr/hal-00936938

M. Andrychowicz, F. Wolski, A. Ray, J. Schneider, R. Fong et al., Hindsight Experience Replay, Nips, 2017.

C. Florensa, D. Held, M. Wulfmeier, and P. Abbeel, Reverse curriculum generation for reinforcement learning, 2017.

J. Schmidhuber, Powerplay: Training an increasingly general problem solver by continually searching for the simplest still unsolvable problem, Frontiers in psychology, vol.4, p.313, 2013.

A. Péré, S. Forestier, O. Sigaud, and P. Oudeyer, Unsupervised Learning of Goal Spaces for Intrinsically Motivated Goal Exploration, ICLR, pp.1-26, 2018.

I. Higgins, L. Matthey, X. Glorot, A. Pal, B. Uria et al., Early Visual Concept Learning with Unsupervised Deep Learning, 2016.

X. Chen, Y. Duan, R. Houthooft, J. Schulman, I. Sutskever et al., InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets, Lecture Notes in Computer Science, vol.9006, 2015.

V. Thomas, E. Bengio, W. Fedus, J. Pondard, P. Beaudoin et al., Disentangling the independently controllable factors of variation by interacting with the world, pp.1-9, 2017.

P. Y. Oudeyer, F. Kaplan, and V. V. Hafner, Intrinsic motivation systems for autonomous mental development, IEEE Transactions on Evolutionary Computation, vol.11, issue.2, pp.265-286, 2007.

Y. Bengio, A. Courville, and P. Vincent, Representation learning: A review and new perspectives, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.35, issue.8, pp.1798-1828, 2013.

I. Higgins, L. Matthey, A. Pal, C. Burgess, X. Glorot et al., beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework, ICLR, number July, pp.1-13, 2017.

S. Forestier and P. Y. Oudeyer, Modular active curiosity-driven discovery of tool use, IEEE International Conference on Intelligent Robots and Systems, pp.3965-3972, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01384566

F. C. Benureau and P. Oudeyer, Behavioral Diversity Generation in Autonomous Exploration through Reuse of Past Experience, Frontiers in Robotics and AI, vol.3, 2016.
URL : https://hal.archives-ouvertes.fr/hal-01404329

D. Pathak, P. Mahmoudieh, G. Luo, P. Agrawal, D. Chen et al., Zero-Shot Visual Imitation, ICLR, pp.1-12, 2018.

C. P. Burgess, I. Higgins, A. Pal, L. Matthey, N. Watters et al., Understanding disentangling in ?-VAE, Nips, 2017.

D. P. Kingma and J. L. Ba, (a) Random Parameterization Exploration (b) Random Goal Exploration with Engineered Features Representation (RGE-EFR) (c) Modular Goal Exploration, International Conference on Learning Representations, pp.1-15, 2015.

, Examples of achieved outcomes together with the ratio of covered cells in the Arm-2-Balls environment for RPE, MGE-EFR and RGE-EFR exploration algorithms. The number of times the ball was effectively handled is also represented. 20 (a) Random Goal Exploration with an entangled representation (VAE) as a goal space, Figure, vol.12

, Modular Goal Exploration with an entangled representation (VAE) as a goal space

, Random Goal Exploration with a disentangled representation (?VAE) as a goal space

. , Modular Goal Exploration with a disentangled representation (?VAE) as a goal space

, Examples of achieved outcomes together with the ratio of covered cells in the Arm-2-Balls environment for MGE and RGE exploration algorithms using learned goal spaces (VAE and ?VAE). The number of times the ball was effectively handled is also represented, Figure, vol.13