Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes

Aus de_evolutionary_art_org
Wechseln zu: Navigation, Suche


Jürgen Schmidhuber: Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes. In: Dagstuhl Seminar 09291 2009: Computational Creativity: An Interdisciplinary Approach.



I argue that data becomes temporarily interesting by itself to some self-improving, but computationally limited, subjective observer once he learns to predict or compress the data in a better way, thus making it subjectively simpler and more "beautiful." Curiosity is the desire to create or discover more non-random, non-arbitrary, regular data that is novel and surprising not in the traditional sense of Boltzmann and Shannon but in the sense that it allows for compression progress because its regularity was not yet known. This drive maximizes interestingness, the first derivative of subjective beauty or compressibility, that is, the steepness of the learning curve. It motivates exploring infants, pure mathematicians, composers, artists, dancers, comedians, yourself, and (since 1990) artificial systems. Compare overview sites with previous papers (1990-2009) on the formal theory of subjective beauty and creativity: and

Extended Abstract


 author =	{Juergen Schmidhuber},
 title =	{Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes.},
 booktitle =	{Computational Creativity: An Interdisciplinary Approach},
 year = 	{2009},
 editor =	{Margaret Boden and Mark D'Inverno and Jon McCormack},
 number =	{09291},
 series =	{Dagstuhl Seminar Proceedings},
 ISSN = 	{1862-4405},
 publisher =	{Schloss Dagstuhl - Leibniz-Zentrum fuer Informatik, Germany},
 address =	{Dagstuhl, Germany},
 URL =		{,,_Novelty,_Surprise,_Interestingness,_Attention,_Curiosity,_Creativity,_Art,_Science,_Music,_Jokes },
 annote =	{Keywords: Subjective Beauty, Surprise, Interestingness, Curiosity, Creativity, Art, Science, Music, Jokes}

Used References

[1] I. Aleksander. The World in My Mind, My Mind In The World: Key Mechanisms of Consciousness in Humans, Animals and Machines. Imprint Academic, 2005.

[2] B. Baars and N. M. Gage. Cognition, Brain and Consciousness: An Introduction to Cognitive Neuroscience. Elsevier / Academic Press, 2007.

[3] M. Balter. Seeking the key to music. Science, 306:1120–1122, 2004.

[4] H. B. Barlow, T. P. Kaushal, and G. J. Mitchison. Finding minimum entropy codes. Neural Computation, 1(3):412–423, 1989.

[5] A. G. Barto, S. Singh, and N. Chentanez. Intrinsically motivated learning of hierarchical collections of skills. In Proceedings of International Conference on Developmental Learning (ICDL). MIT Press, Cambridge, MA, 2004.

[6] M. Bense. Einf ̈uhrung in die informationstheoretische Asthetik. Grundlegung und Anwendung in der Texttheorie (Introduction to information-theoretical aes- thetics. Foundation and application to text theory). Rowohlt Taschenbuch Ver- lag, 1969.

[7] G. D. Birkhoff. Aesthetic Measure. Harvard University Press, 1933.

[8] C. M. Bishop. Neural networks for pattern recognition. Oxford University Press, 1995.

[9] D. Blank and L. Meeden. Developmental Robotics AAAI Spring Symposium, Stanford, CA, 2005.

[10] D. Blank and L. Meeden. Introduction to the special issue on developmental robotics. Connection Science, 18(2), 2006.

[11] J. C. Bongard and H. Lipson. Nonlinear system identification using coevolution of models and tests. IEEE Transactions on Evolutionary Computation, 9(4), 2005.

[12] M. V. Butz. How and why the brain lays the foundations for a conscious self. Constructivist Foundations, 4(1):1–14, 2008.

[13] L. D. Ca ̃namero. Designing emotions for activity selection in autonomous agents. In R. Trappl, P. Petta, and S. Payr, editors, Emotions in Humans and Artifacts, pages 115–148. The MIT Press, Cambridge, MA, 2003.

[14] D. A. Cohn. Neural network exploration using optimal experiment design. In J. Cowan, G. Tesauro, and J. Alspector, editors, Advances in Neural Information Processing Systems 6, pages 679–686. Morgan Kaufmann, 1994.

[15] N. L. Cramer. A representation for the adaptive generation of simple sequential programs. In J.J. Grefenstette, editor, Proceedings of an International Confer- ence on Genetic Algorithms and Their Applications, Carnegie-Mellon Univer- sity, July 24-26, 1985, Hillsdale NJ, 1985. Lawrence Erlbaum Associates.

[16] V. V. Fedorov. Theory of optimal experiments. Academic Press, 1972.

[17] F. Galton. Composite portraits made by combining those of many different per- sons into a single figure. Nature, 18(9):97–100, 1878.

[18] K. G ̈odel. Uber formal unentscheidbare S ̈atze der Principia Mathematica und verwandter Systeme I. Monatshefte f ̈ur Mathematik und Physik, 38:173–198, 1931.

[19] F. J. Gomez. Robust Nonlinear Control through Neuroevolution. PhD thesis, Department of Computer Sciences, University of Texas at Austin, 2003.

[20] F. J. Gomez and R. Miikkulainen. Incremental evolution of complex general behavior. Adaptive Behavior, 5:317–342, 1997.

[21] F. J. Gomez and R. Miikkulainen. Solving non-Markovian control tasks with neuroevolution. In Proc. IJCAI 99, Denver, CO, 1999. Morgan Kaufman.

[22] F. J. Gomez and R. Miikkulainen. Active guidance for a finless rocket using neuroevolution. In Proc. GECCO 2003, Chicago, 2003. Winner of Best Paper Award in Real World Applications. Gomez is working at IDSIA on a CSEM grant to J. Schmidhuber.

[23] F. J. Gomez and J. Schmidhuber. Co-evolving recurrent neurons learn deep memory POMDPs. In Proc. of the 2005 conference on genetic and evolutionary computation (GECCO), Washington, D. C. ACM Press, New York, NY, USA, 2005. Nominated for a best paper award.

[24] F. J. Gomez, J. Schmidhuber, and R. Miikkulainen. Efficient non-linear control through neuroevolution. Journal of Machine Learning Research JMLR, 9:937– 965, 2008.

[25] P. Haikonen. The Cognitive Approach to Conscious Machines. Imprint Aca- demic, 2003.

[26] S. Hochreiter and J. Schmidhuber. Long short-term memory. Neural Computa- tion, 9(8):1735–1780, 1997.

[27] J. H. Holland. Adaptation in Natural and Artificial Systems. University of Michi- gan Press, Ann Arbor, 1975.

[28] D. A. Huffman. A method for construction of minimum-redundancy codes. Proceedings IRE, 40:1098–1101, 1952.

[29] M. Hutter. Universal Artificial Intelligence: Sequential Decisions based on Al- gorithmic Probability. Springer, Berlin, 2004. (On J. Schmidhuber’s SNF grant 20-61847).

[30] M. Hutter. On universal prediction and Bayesian confirmation. Theoretical Computer Science, 2007.

[31] J. Hwang, J. Choi, S. Oh, and R. J. Marks II. Query-based learning applied to partially trained multilayer perceptrons. IEEE Transactions on Neural Networks, 2(1):131–136, 1991.

[32] L. Itti and P. F. Baldi. Bayesian surprise attracts human attention. In Advances in Neural Information Processing Systems 19, pages 547–554. MIT Press, Cam- bridge, MA, 2005.

[33] L. P. Kaelbling, M. L. Littman, and A. W. Moore. Reinforcement learning: a survey. Journal of AI research, 4:237–285, 1996.

[34] A. N. Kolmogorov. Three approaches to the quantitative definition of informa- tion. Problems of Information Transmission, 1:1–11, 1965.

[35] S. Kullback. Statistics and Information Theory. J. Wiley and Sons, New York, 1959.

[36] L. A. Levin. Universal sequential search problems. Problems of Information Transmission, 9(3):265–266, 1973.

[37] M. Li and P. M. B. Vit ́anyi. An Introduction to Kolmogorov Complexity and its Applications (2nd edition). Springer, 1997.

[38] D. J. C. MacKay. Information-based objective functions for active data selection. Neural Computation, 4(2):550–604, 1992.

[39] O. Miglino, H. Lund, and S. Nolfi. Evolving mobile robots in simulated and real environments. Artificial Life, 2(4):417–434, 1995.

[40] G. Miller, P. Todd, and S. Hedge. Designing neural networks using genetic algorithms. In Proceedings of the 3rd International Conference on Genetic Al- gorithms, pages 379–384. Morgan Kauffman, 1989.

[41] A. Moles. Information Theory and Esthetic Perception. Univ. of Illinois Press, 1968.

[42] D. E. Moriarty and P. Langley. Learning cooperative lane selection strategies for highways. In Proceedings of the Fifteenth National Conference on Artificial Intelligence (AAAI-98), pages 684–691, Madison, WI, 1998.

[43] D. E. Moriarty and R. Miikkulainen. Efficient reinforcement learning through symbiotic evolution. Machine Learning, 22:11–32, 1996.

[44] F. Nake. Asthetik als Informationsverarbeitung. Springer, 1974.

[45] S. Nolfi, D. Floreano, O. Miglino, and F. Mondada. How to evolve autonomous robots: Different approaches in evolutionary robotics. In R. A. Brooks and P. Maes, editors, Fourth International Workshop on the Synthesis and Simulation of Living Systems (Artificial Life IV), pages 190–197. MIT, 1994.

[46] J. R. Olsson. Inductive functional programming using incremental program transformation. Artificial Intelligence, 74(1):55–83, 1995.

[47] B. A. Pearlmutter. Gradient calculations for dynamic recurrent neural networks: A survey. IEEE Transactions on Neural Networks, 6(5):1212–1228, 1995.

[48] D. I. Perrett, K . A. May, and S. Yoshikawa. Facial shape and judgements of female attractiveness. Nature, 368:239–242, 1994.

[49] J. Piaget. The Child’s Construction of Reality. London: Routledge and Kegan Paul, 1955.

[50] S. Pinker. How the mind works. Norton, W. W. & Company, Inc., 1997.

[51] M. Plutowski, G. Cottrell, and H. White. Learning Mackey-Glass from 25 ex- amples, plus or minus 2. In J. Cowan, G. Tesauro, and J. Alspector, editors, Advances in Neural Information Processing Systems 6, pages 1135–1142. Mor- gan Kaufmann, 1994.

[52] J. Poland and M. Hutter. Strong asymptotic assertions for discrete MDL in re- gression and classification. In Annual Machine Learning Conference of Belgium and the Netherlands (Benelearn-2005), Enschede, 2005.

[53] I. Rechenberg. Evolutionsstrategie - Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. Dissertation, 1971. Published 1973 by Fromman-Holzboog.

[54] J. Rissanen. Modeling by shortest data description. Automatica, 14:465–471, 1978.

[55] A. J. Robinson and F. Fallside. The utility driven dynamic error propagation network. Technical Report CUED/F-INFENG/TR.1, Cambridge University En- gineering Department, 1987.

[56] T. R ̈uckstieß, M. Felder, and J. Schmidhuber. State-Dependent Exploration for policy gradient methods. In W. Daelemans et al., editor, European Conference on Machine Learning (ECML) and Principles and Practice of Knowledge Dis- covery in Databases 2008, Part II, LNAI 5212, pages 234–249, 2008.

[57] J. Schmidhuber. Dynamische neuronale Netze und das fundamentale raumzeitliche Lernproblem. Dissertation, Institut f ̈ur Informatik, Technische Universit ̈at M ̈unchen, 1990.

[58] J. Schmidhuber. Making the world differentiable: On using fully recurrent self- supervised neural networks for dynamic reinforcement learning and planning in non-stationary environments. Technical Report FKI-126-90, Institut f ̈ur Infor- matik, Technische Universit ̈at M ̈unchen, 1990.

[59] J. Schmidhuber. Adaptive curiosity and adaptive confidence. Technical Re- port FKI-149-91, Institut f ̈ur Informatik, Technische Universit ̈at M ̈unchen, April 1991. See also [60].

[60] J. Schmidhuber. Curious model-building control systems. In Proceedings of the International Joint Conference on Neural Networks, Singapore, volume 2, pages 1458–1463. IEEE press, 1991.

[61] J. Schmidhuber. A possibility for implementing curiosity and boredom in model- building neural controllers. In J. A. Meyer and S. W. Wilson, editors, Proc. of the International Conference on Simulation of Adaptive Behavior: From Animals to Animats, pages 222–227. MIT Press/Bradford Books, 1991.

[62] J. Schmidhuber. A fixed size storage O(n3 ) time complexity learning algo- rithm for fully recurrent continually running networks. Neural Computation, 4(2):243–248, 1992.

[63] J. Schmidhuber. Learning complex, extended sequences using the principle of history compression. Neural Computation, 4(2):234–242, 1992.

[64] J. Schmidhuber. Learning factorial codes by predictability minimization. Neural Computation, 4(6):863–879, 1992.

[65] J. Schmidhuber. A computer scientist’s view of life, the universe, and every- thing. In C. Freksa, M. Jantzen, and R. Valk, editors, Foundations of Computer Science: Potential - Theory - Cognition, volume 1337, pages 201–208. Lecture Notes in Computer Science, Springer, Berlin, 1997.

[66] J. Schmidhuber. Femmes fractales, 1997.

[67] J. Schmidhuber. Low-complexity art. Leonardo, Journal of the International Society for the Arts, Sciences, and Technology, 30(2):97–103, 1997.

[68] J. Schmidhuber. What’s interesting? Technical Report IDSIA-35-97, IDSIA, 1997.; extended abstract in Proc. Snowbird’98, Utah, 1998; see also [72].

[69] J. Schmidhuber. Facial beauty and fractal geometry. Technical Report TR IDSIA-28-98, IDSIA, 1998. Published in the Cogprint Archive:

[70] J. Schmidhuber. Algorithmic theories of everything. Technical Report IDSIA- 20-00, quant-ph/0011122, IDSIA, Manno (Lugano), Switzerland, 2000. Sec- tions 1-5: see [73]; Section 6: see [74].

[71] J. Schmidhuber. Sequential decision making based on direct search. In R. Sun and C. L. Giles, editors, Sequence Learning: Paradigms, Algorithms, and Ap- plications. Springer, 2001. Lecture Notes on AI 1828.

[72] J. Schmidhuber. Exploring the predictable. In A. Ghosh and S. Tsuitsui, editors, Advances in Evolutionary Computing, pages 579–612. Springer, 2002.

[73] J. Schmidhuber. Hierarchies of generalized Kolmogorov complexities and nonenumerable universal measures computable in the limit. International Jour- nal of Foundations of Computer Science, 13(4):587–612, 2002.

[74] J. Schmidhuber. The Speed Prior: a new simplicity measure yielding near- optimal computable predictions. In J. Kivinen and R. H. Sloan, editors, Pro- ceedings of the 15th Annual Conference on Computational Learning Theory (COLT 2002), Lecture Notes in Artificial Intelligence, pages 216–228. Springer, Sydney, Australia, 2002.

[75] J. Schmidhuber. Optimal ordered problem solver. Machine Learning, 54:211– 254, 2004.

[76] J. Schmidhuber. Overview of artificial curiosity and ac- tive exploration, with links to publications since 1990, 2004. ̃juergen/interest.html.

[77] J. Schmidhuber. Overview of work on robot learning, with publications, 2004. ̃juergen/learningrobots.html.

[78] J. Schmidhuber. RNN overview, with links to a dozen journal publications, 2004. ̃juergen/rnn.html.

[79] J. Schmidhuber. Completely self-referential optimal reinforcement learners. In W. Duch, J. Kacprzyk, E. Oja, and S. Zadrozny, editors, Artificial Neural Net- works: Biological Inspirations - ICANN 2005, LNCS 3697, pages 223–233. Springer-Verlag Berlin Heidelberg, 2005. Plenary talk.

[80] J. Schmidhuber. G ̈odel machines: Towards a technical justification of conscious- ness. In D. Kudenko, D. Kazakov, and E. Alonso, editors, Adaptive Agents and Multi-Agent Systems III (LNCS 3394), pages 1–23. Springer Verlag, 2005.

[81] J. Schmidhuber. Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts. Connection Science, 18(2):173–187, 2006.

[82] J. Schmidhuber. G ̈odel machines: Fully self-referential optimal universal self-improvers. In B. Goertzel and C. Pennachin, editors, Artificial Gen- eral Intelligence, pages 199–226. Springer Verlag, 2006. Variant available as arXiv:cs.LO/0309048.

[83] J. Schmidhuber. The new AI: General & sound & relevant for physics. In B. Go- ertzel and C. Pennachin, editors, Artificial General Intelligence, pages 175–198. Springer, 2006. Also available as TR IDSIA-04-03, arXiv:cs.AI/0302012.

[84] J. Schmidhuber. Randomness in physics. Nature, 439(3):392, 2006. Correspon- dence.

[85] J. Schmidhuber. 2006: Celebrating 75 years of AI - history and outlook: the next 25 years. In M. Lungarella, F. Iida, J. Bongard, and R. Pfeifer, editors, 50 Years of Artificial Intelligence, volume LNAI 4850, pages 29–41. Springer Berlin / Heidelberg, 2007. Preprint available as arXiv:0708.4311.

[86] J. Schmidhuber. New millennium AI and the convergence of history. In W. Duch and J. Mandziuk, editors, Challenges to Computational Intelligence, volume 63, pages 15–36. Studies in Computational Intelligence, Springer, 2007. Also avail- able as arXiv:cs.AI/0606081.

[87] J. Schmidhuber. Simple algorithmic principles of discovery, subjective beauty, selective attention, curiosity & creativity. In Proc. 18th Intl. Conf. on Algo- rithmic Learning Theory (ALT 2007), LNAI 4754, pages 32–33. Springer, 2007. Joint invited lecture for ALT 2007 and DS 2007, Sendai, Japan, 2007.

[88] J. Schmidhuber. Simple algorithmic principles of discovery, subjective beauty, selective attention, curiosity & creativity. In Proc. 10th Intl. Conf. on Discov- ery Science (DS 2007), LNAI 4755, pages 26–38. Springer, 2007. Joint invited lecture for ALT 2007 and DS 2007, Sendai, Japan, 2007.

[89] J. Schmidhuber. Driven by compression progress. In I. Lovrek, R. J. Howlett, and L. C. Jain, editors, Knowledge-Based Intelligent Information and Engineer- ing Systems KES-2008, Lecture Notes in Computer Science LNCS 5177, Part I, page 11. Springer, 2008. Abstract of invited keynote.

[90] J. Schmidhuber. Driven by compression progress: A simple principle explains essential aspects of subjective beauty, novelty, surprise, interestingness, atten- tion, curiosity, creativity, art, science, music, jokes. In G. Pezzulo, M. V. Butz, O. Sigaud, and G. Baldassarre, editors, Anticipatory Behavior in Adaptive Learning Systems, from Sensorimotor to Higher-level Cognitive Capabilities, LNAI. Springer, 2009. In press.

[91] J. Schmidhuber. Simple algorithmic theory of subjective beauty, novelty, sur- prise, interestingness, attention, curiosity, creativity, art, science, music, jokes. Journal of SICE, 48(1):21–32, 2009.

[92] J. Schmidhuber. Ultimate cognition a` la G ̈odel. Cognitive Computation, 2009, in press.

[93] J. Schmidhuber and B. Bakker. NIPS 2003 workshop on recurrent neural networks, Whistler, ̃juergen/rnnaissance.html. RNNaissance CA, 2003.

[94] J. Schmidhuber, A. Graves, F. J. Gomez, S. Fernandez, and S. Hochreiter. How to Learn Programs with Artificial Recurrent Neural Networks. Invited by Cam- bridge University Press, 2009. In preparation.

[95] J. Schmidhuber and S. Heil. Sequential neural text compression. IEEE Trans- actions on Neural Networks, 7(1):142–146, 1996.

[96] J. Schmidhuber and R. Huber. Learning to generate artificial fovea trajectories for target detection. International Journal of Neural Systems, 2(1 & 2):135–141, 1991.

[97] J. Schmidhuber, J. Zhao, and N. Schraudolph. Reinforcement learning with self- modifying policies. In S. Thrun and L. Pratt, editors, Learning to learn, pages 293–309. Kluwer, 1997.

[98] J. Schmidhuber, J. Zhao, and M. Wiering. Shifting inductive bias with success- story algorithm, adaptive Levin search, and incremental self-improvement. Ma- chine Learning, 28:105–130, 1997.

[99] H. P. Schwefel. Numerische Optimierung von Computer-Modellen. Disserta- tion, 1974. Published 1977 by Birkh ̈auser, Basel.

[100] F. Sehnke, C. Osendorfer, T. R ̈uckstieß, A. Graves, J. Peters, and J. Schmid- huber. Policy gradients with parameter-based exploration for control. In Pro- ceedings of the International Conference on Artificial Neural Networks ICANN, 2008.

[101] A. K. Seth, E. Izhikevich, G. N. Reeke, and G. M. Edelman. Theories and measures of consciousness: An extended framework. Proc. Natl. Acad. Sciences USA, 103:10799–10804, 2006.

[102] C. E. Shannon. A mathematical theory of communication (parts I and II). Bell System Technical Journal, XXVII:379–423, 1948.

[103] K. Sims. Evolving virtual creatures. In Andrew Glassner, editor, Proceedings of SIGGRAPH ’94 (Orlando, Florida, July 1994), Computer Graphics Proceed- ings, Annual Conference, pages 15–22. ACM SIGGRAPH, ACM Press, jul 1994. ISBN 0-89791-667-0.

[104] S. Singh, A. G. Barto, and N. Chentanez. Intrinsically motivated reinforcement learning. In Advances in Neural Information Processing Systems 17 (NIPS). MIT Press, Cambridge, MA, 2005.

[105] A. Sloman and R. L. Chrisley. Virtual machines and consciousness. Journal of Consciousness Studies, 10(4-5):113–172, 2003.

[106] R. J. Solomonoff. A formal theory of inductive inference. Part I. Information and Control, 7:1–22, 1964.

[107] R. J. Solomonoff. Complexity-based induction systems. IEEE Transactions on Information Theory, IT-24(5):422–432, 1978.

[108] J. Storck, S. Hochreiter, and J. Schmidhuber. Reinforcement driven informa- tion acquisition in non-deterministic environments. In Proceedings of the In- ternational Conference on Artificial Neural Networks, Paris, volume 2, pages 159–164. EC2 & Cie, 1995.

[109] R. Sutton and A. Barto. Reinforcement learning: An introduction. Cambridge, MA, MIT Press, 1998.

[110] R. S. Sutton, D. A. McAllester, S. P. Singh, and Y. Mansour. Policy gradient methods for reinforcement learning with function approximation. In S. A. Solla, T. K. Leen, and K.-R. M ̈uller, editors, Advances in Neural Information Pro- cessing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29 - December 4, 1999], pages 1057–1063. The MIT Press, 1999.

[111] A. M. Turing. On computable numbers, with an application to the Entschei- dungsproblem. Proceedings of the London Mathematical Society, Series 2, 41:230–267, 1936.

[112] C. S. Wallace and D. M. Boulton. An information theoretic measure for classi- fication. Computer Journal, 11(2):185–194, 1968.

[113] C. S. Wallace and P. R. Freeman. Estimation and inference by compact coding. Journal of the Royal Statistical Society, Series ”B”, 49(3):240–265, 1987.

[114] C. J. C. H. Watkins. Learning from Delayed Rewards. PhD thesis, King’s Col- lege, Oxford, 1989.

[115] P. J. Werbos. Generalization of backpropagation with application to a recurrent gas market model. Neural Networks, 1, 1988.

[116] S.D. Whitehead. Reinforcement Learning for the adaptive control of perception and action. PhD thesis, University of Rochester, February 1992.

[117] D. Wierstra, T. Schaul, J. Peters, and J. Schmidhuber. Fitness expectation maxi- mization. In Proceedings of Parallel Problem Solving from Nature (PPSN 2008), 2008.

[118] D. Wierstra, T. Schaul, J. Peters, and J. Schmidhuber. Natural evolution strate- gies. In Congress of Evolutionary Computation (CEC 2008), 2008.

[119] D. Wierstra and J. Schmidhuber. Policy gradient critics. In Proceedings of the 18th European Conference on Machine Learning (ECML 2007), 2007.

[120] R. J. Williams and D. Zipser. Gradient-based learning algorithms for recurrent networks and their computational complexity. In Back-propagation: Theory, Architectures and Applications. Hillsdale, NJ: Erlbaum, 1994.

[121] B. M. Yamauchi and R. D. Beer. Sequential behavior and learning in evolved dynamical neural networks. Adaptive Behavior, 2(3):219–246, 1994.

[122] Xin Yao. A review of evolutionary artificial neural networks. International Journal of Intelligent Systems, 4:203–222, 1993.

[123] K. Zuse. Rechnender Raum. Elektronische Datenverarbeitung, 8:336–344, 1967.

[124] K. Zuse. Rechnender Raum. Friedrich Vieweg & Sohn, Braunschweig, 1969. English translation: Calculating Space, MIT Technical Translation AZT-70- 164-GEMIT, Massachusetts Institute of Technology (Proj. MAC), Cambridge, Mass. 02139, Feb. 1970.


Full Text

intern file

Sonstige Links