Transforming Exploratory Creativity with DeLeNoX

Aus de_evolutionary_art_org
Version vom 12. November 2015, 13:32 Uhr von Gubachelier (Diskussion | Beiträge)

(Unterschied) ← Nächstältere Version | Aktuelle Version (Unterschied) | Nächstjüngere Version → (Unterschied)
Wechseln zu: Navigation, Suche


Reference

Antonios Liapis, Héctor P. Martínez, Julian Togelius and Georgios N. Yannakakis: Transforming Exploratory Creativity with DeLeNoX. In: Computational Creativity 2013 ICCC 2013, 56-63.

DOI

Abstract

We introduce DeLeNoX (Deep Learning Novelty Ex- plorer), a system that autonomously creates artifacts in constrained spaces according to its own evolving inter- estingness criterion. DeLeNoX proceeds in alternating phases of exploration and transformation. In the explo- ration phases, a version of novelty search augmented with constraint handling searches for maximally diverse artifacts using a given distance function. In the trans- formation phases, a deep learning autoencoder learns to compress the variation between the found artifacts into a lower-dimensional space. The newly trained encoder is then used as the basis for a new distance function, transforming the criteria for the next exploration phase. In the current paper, we apply DeLeNoX to the cre- ation of spaceships suitable for use in two-dimensional arcade-style computer games, a representative problem in procedural content generation in games. We also sit- uate DeLeNoX in relation to the distinction between ex- ploratory and transformational creativity, and in relation to Schmidhuber’s theory of creativity through the drive for compression progress.

Extended Abstract

Bibtex

@inproceedings{
author = {Antonios Liapis, Héctor P. Martínez, Julian Togelius and Georgios N. Yannakakis},
title = {Transforming Exploratory Creativity with DeLeNoX},
editor = {Simon Colton, Dan Ventura, Nada Lavrač, Michael Cook},
booktitle = {Proceedings of the Fourth International Conference on Computational Creativity},
series = {ICCC2013},
year = {2013},
month = {Jun},
location = {Sydney, New South Wales, Australia},
pages = {56-63},
url = {http://www.computationalcreativity.net/iccc2013/download/iccc2013-liapis-et-al.pdf, http://de.evo-art.org/index.php?title=Transforming_Exploratory_Creativity_with_DeLeNoX },
publisher = {International Association for Computational Creativity},
keywords = {computational, creativity},
}

Used References

Baluja, S.; Pomerleau, D.; and Jochem, T. 1999. Towards automated artificial evolution for computer-generated im- ages. Musical networks 341–370.

Bengio, Y. 2009. Learning deep architectures for AI. Foun- dations and Trends in Machine Learning 2(1):1–127. Boden, M. 1990. The Creative Mind. Abacus.

Correia, J.; Machado, P.; Romero, J.; and Carballal, A. 2013. Feature selection and novelty in computational aesthetics. In Proceedings of the International Conference on Evolution- ary and Biologically Inspired Music, Sound, Art and Design, 133–144.

Csikszentmihalyi, M. 1996. Creativity-flow and the psy- chology of discovery and invention. Harper perennial.

De Bono, E. 1970. Lateral thinking: creativity step by step. Harper & Row.

Hinton, G. E., and Zemel, R. S. Autoencoders, minimum description length, and helmholtz free energy. In Advances in Neural Information Processing Systems.

Kimbrough, S. O.; Koehler, G. J.; Lu, M.; and Wood, D. H. 2008. On a feasible-infeasible two-population (fi-2pop) ge- netic algorithm for constrained optimization: Distance trac- ing and no free lunch. European Journal of Operational Research 190(2):310–327.

Koster, R., and Wright, W. 2004. A Theory of Fun for Game Design. Paraglyph Press.

Kuhn, T. S. 1962. The Structure of Scientific Revolutions. University of Chicago Press.

Lehman, J., and Stanley, K. O. 2011. Abandoning objec- tives: Evolution through the search for novelty alone. Evo- lutionary Computation 19(2):189–223.

Liapis, A.; Yannakakis, G. N.; and Togelius, J. 2011a. Neuroevolutionary constrained optimization for content cre- ation. In Proceedings of IEEE Conference on Computational Intelligence and Games, 71–78.

Liapis, A.; Yannakakis, G. N.; and Togelius, J. 2011b. Opti- mizing visual properties of game content through neuroevo- lution. In Artificial Intelligence for Interactive Digital En- tertainment Conference.

Liapis, A.; Yannakakis, G. N.; and Togelius, J. 2012. Adapt- ing models of visual aesthetics for personalized content cre- ation. IEEE Transactions on Computational Intelligence and AI in Games 4(3):213–228.

Liapis, A.; Yannakakis, G.; and Togelius, J. 2013. Enhance- ments to constrained novelty search: Two-population nov- elty search for generating game content. In Proceedings of Genetic and Evolutionary Computation Conference.

Machado, P.; Romero, J.; Manaris, B.; Santos, A.; and Car- doso, A. 2003. Power to the critics — A framework for the development of artificial art critics. In IJCAI 2003 Workshop on Creative Systems.

Machado, P.; Romero, J.; Santos, A.; Cardoso, A.; and Pa- zos, A. 2007. On the development of evolutionary artificial artists. Computers & Graphics 31(6):818 – 826.

Mitchell, T. M. 1997. Machine Learning. McGraw-Hill. Rumelhart, D. 1995. Backpropagation: theory, architec- tures, and applications. Lawrence Erlbaum.

Schmidhuber, J. 2006. Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts. Con- nection Science 18(2):173–187.

Schmidhuber, J. 2007. Simple algorithmic principles of discovery, subjective beauty, selective attention, curiosity & creativity. Lecture Notes in Computer Science 4755:26–38.

Stanley, K. O., and Miikkulainen, R. 2002. Evolving neu- ral networks through augmenting topologies. Evolutionary Computation 10(2):99–127.

Stanley, K. O. 2006. Exploiting regularity without devel- opment. In Proceedings of the AAAI Fall Symposium on Developmental Systems. Menlo Park, CA: AAAI Press.

Togelius, J.; Yannakakis, G.; Stanley, K.; and Browne, C. 2011. Search-based procedural content generation: A tax- onomy and survey. IEEE Transactions on Computational Intelligence and AI in Games (99).

Vincent, P.; Larochelle, H.; Bengio, Y.; and Manzagol, P.- A. 2008. Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th Interna- tional Conference on Machine learning, 1096–1103.

Vygotsky, L.; Rieber, R.; Carton, A.; Wollock, J.; and Glick, J. 1987. The Collected Works of L.S. Vygotsky: Scientific legacy. Cognition and Language. Plenum Press.

Wiggins, G. A. 2006. A preliminary framework for description, analysis and comparison of creative systems. Knowledge-Based Systems 19(7):449–458.

Yannakakis, G. N. 2012. Game AI revisited. In Proceedings of ACM Computing Frontiers Conference.


Links

Full Text

http://www.computationalcreativity.net/iccc2013/download/iccc2013-liapis-et-al.pdf

intern file

Sonstige Links