Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Creativity and Markov Decision Processes (2405.14966v1)

Published 23 May 2024 in cs.AI

Abstract: Creativity is already regularly attributed to AI systems outside specialised computational creativity (CC) communities. However, the evaluation of creativity in AI at large typically lacks grounding in creativity theory, which can promote inappropriate attributions and limit the analysis of creative behaviour. While CC researchers have translated psychological theory into formal models, the value of these models is limited by a gap to common AI frameworks. To mitigate this limitation, we identify formal mappings between Boden's process theory of creativity and Markov Decision Processes (MDPs), using the Creative Systems Framework as a stepping stone. We study three out of eleven mappings in detail to understand which types of creative processes, opportunities for (aberrations), and threats to creativity (uninspiration) could be observed in an MDP. We conclude by discussing quality criteria for the selection of such mappings for future work and applications.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (48)
  1. 2023. Interdisciplinary methods in computational creativity: How human variables shape human-inspired AI research. In Proceedings of the International Conference on Computational Creativity.
  2. 2022. Five properties of specific curiosity you didn’t know curious machines should have. arXiv preprint arXiv:2212.00187.
  3. 2015. Dev er: A computational model of early cognitive development as a creative process. Cognitive Systems Research 33:17–41.
  4. Besold, T. R. 2016. The unnoticed creativity revolutions: Bringing problem-solving back into computational creativity. In Proceedings of the AISB International Symposium on Computational Creativity, 1–8. CRC Press, Taylor & Francis Group.
  5. 2022. Interpreting systems as solving POMDPs: a step towards a formal understanding of agency. In International Workshop on Active Inference, 16–31. Springer.
  6. Boden, M. A. 2004. The Creative Mind: Myths and Mechanisms. London, UK: Routledge. First published in 1990.
  7. Boden, M. A. 2013. Creativity as a neuroscientific mystery. In Vartanian, O.; Bristol, A. S.; and Kaufman, J. C., eds., Neuroscience of Creativity. MIT Press. 3–18.
  8. Boden, M. A. 2015. How computational creativity began. In Besold, T. R.; Schorlemmer, M.; and Smaill, A., eds., Computational Creativity Research: Towards Creative Machines. Atlantis Press. 5–13.
  9. Bory, P. 2019. Deep new: The shifting narratives of artificial intelligence from Deep Blue to AlphaGo. Convergence 25(4):627–642.
  10. 2010. Approximate dynamic programming with a fuzzy parameterization. Automatica 46(5):804–814.
  11. 2016. Hierarchical reinforcement learning as creative problem solving. Robotics and Autonomous Systems 86:196–206.
  12. 2012. Computational creativity: The final frontier? In Proc. ECAI, volume 12, 21–26.
  13. 2011. Computational creativity theory: The face and idea descriptive models. In Proceedings of the International Conference on Computational Creativity, 90–95. Mexico City.
  14. Colton, S. 2008. Creativity versus the perception of creativity in computational systems. In AAAI Spring Symposium: Creative Intelligent Systems, volume 8,  7. Palo Alto, CA.
  15. 2018. Neighbouring Communities: Interaction, Lessons and Opportunities. In Proceedings of the International Conference on Computational Creativity, 256–263. Association for Computational Creativity.
  16. 2015. Specific curiosity as a cause and consequence of transformational creativity. In Proceedings of the International Conference on Computational Creativity, 260–267.
  17. 2023. The process definition of creativity. Creativity Research Journal 1–29.
  18. Jennings, K. E. 2010. Developing creativity: Artificial barriers in artificial intelligence. Minds and Machines 20:489–501.
  19. Jordanous, A. 2016. Four PPPPerspectives on computational creativity in theory and in practice. Connection Science 28(2):194–216.
  20. 2016. Modes for creative human-computer collaboration: Alternating and task-divided co-creativity. In Proceedings of the International Conference on Computational Creativity, 77–84.
  21. 2023. Discovering agents. Artificial Intelligence 322:103963.
  22. 2019. The two-fold model of creativity: the neural underpinnings of the generation and evaluation of creative ideas. Current Opinion in Behavioral Sciences 27:131–138. Creativity.
  23. 2018. Evaluating computational creativity: An interdisciplinary tutorial. ACM Computing Surveys (CSUR) 51(2):1–34.
  24. 2017. Markov Chains and Mixing Times: Second Edition. American Mathematical Society.
  25. 2019. Extending the creative systems framework for the analysis of creative agent societies. In Proceedings of the International Conference on Computational Creativity. Association for Computational Creativity.
  26. 2020. Action selection in the creative systems framework. In Proceedings of the International Conference on Computational Creativity.
  27. 2024. Advancing self-determination theory with computational intrinsic motivation: The case of competence. osf.io/preprints/psyarxiv/4cbuv.
  28. 2017. Adaptive state space partitioning of Markov decision processes for elastic resource management. In Proceedings of the IEEE International Conference on Data Engineering, 191–194.
  29. Markov, A. A. 1906. Extension of the law of large numbers to dependent events. Izvestiia Fiz.-Matem. Obsch. Kazan Univ. 2:135–156. (In Russian).
  30. 2006. A proposal for the Dartmouth summer research project on artificial intelligence. AI Magazine 27(4):12–12. First published in 1955.
  31. 2016. Asynchronous methods for deep reinforcement learning. In Balcan, M. F., and Weinberger, K. Q., eds., Proceedings of the International Conference on Machine Learning, volume 48, 1928–1937.
  32. 2022. The Lovelace effect: Perceptions of creativity in machines. New Media & Society 14614448221077278.
  33. 2019. Addressing the theory crisis in psychology. Psychonomic Bulletin & Review 26:1596–1618.
  34. Pérez y Pérez, R. 2018. The computational creativity continuum. In Proceedings of the International Conference on Computational Creativity.
  35. Rhodes, M. 1961. An Analysis of Creativity. The Phi Delta Kappan 42(7):305–310.
  36. Ritchie, G. D. 2012. A closer look at creativity as search. In Proceedings of the International Conference on Computational Creativity, 41–48. Open University Press.
  37. 2012. The standard definition of creativity. Creativity Research Journal 24(1):92–96.
  38. Saunders, R. 2012. Towards autonomous creative systems: A computational approach. Cognitive Computation 4:216–225.
  39. 2018. Reinforcement Learning: An Introduction. Massachusetts, USA: MIT Press.
  40. 1999. Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning. Artificial intelligence 112(1-2):181–211.
  41. Sutton, R. S. 1997. On the significance of Markov decision processes. In Gerstner, W.; Germond, A.; Hasler, M.; and Nicoud, J.-D., eds., Artificial Neural Networks — ICANN’97, 273–282. Berlin, Heidelberg: Springer Berlin Heidelberg.
  42. 2023. Reclaiming AI as a theoretical tool for cognitive science. osf.io/preprints/psyarxiv/4cbuv.
  43. Walia, C. 2019. A dynamic definition of creativity. Creativity Research Journal 31(3):237–247.
  44. Wallas, G. 1926. The Art of Thought, volume 10. Harcourt, Brace.
  45. 2018. Computational creativity and live algorithms. In The Oxford Handbook of Algorithmic Music. Oxford University Press.
  46. Wiggins, G. A. 2006a. A preliminary framework for description, analysis and comparison of creative systems. Knowledge-Based Systems 19(7):449–458.
  47. Wiggins, G. A. 2006b. Searching for computational creativity. New Generation Computing 24:209–222.
  48. Wiggins, G. A. 2019. A framework for description, analysis and comparison of creative systems. In Computational Synthesis and Creative Systems. Springer International Publishing. 21–47.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Joonas Lahikainen (2 papers)
  2. Nadia M. Ady (8 papers)
  3. Christian Guckelsberger (20 papers)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets