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

Evolving Neural Networks Reveal Emergent Collective Behavior from Minimal Agent Interactions (2410.19718v1)

Published 25 Oct 2024 in nlin.AO, cs.AI, and cs.MA

Abstract: Understanding the mechanisms behind emergent behaviors in multi-agent systems is critical for advancing fields such as swarm robotics and artificial intelligence. In this study, we investigate how neural networks evolve to control agents' behavior in a dynamic environment, focusing on the relationship between the network's complexity and collective behavior patterns. By performing quantitative and qualitative analyses, we demonstrate that the degree of network non-linearity correlates with the complexity of emergent behaviors. Simpler behaviors, such as lane formation and laminar flow, are characterized by more linear network operations, while complex behaviors like swarming and flocking show highly non-linear neural processing. Moreover, specific environmental parameters, such as moderate noise, broader field of view, and lower agent density, promote the evolution of non-linear networks that drive richer, more intricate collective behaviors. These results highlight the importance of tuning evolutionary conditions to induce desired behaviors in multi-agent systems, offering new pathways for optimizing coordination in autonomous swarms. Our findings contribute to a deeper understanding of how neural mechanisms influence collective dynamics, with implications for the design of intelligent, self-organizing systems.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (53)
  1. P. W. Anderson. More is different. Science, 177:393–396, 1972.
  2. B. Alberts. Molecular biology of the cell, volume 3. Garland Publ., 270 Madison Ave., New York, NY, 1994.
  3. I. Couzin. Collective minds. Nature, 445:715–715, 2 2007.
  4. Self-organization and artificial life. Artif. Life, 26:391–408, 9 2020.
  5. J. M. Muñoz. The physics of emergence. Philos. Q., 72:788–791, 6 2022.
  6. Growth, innovation, scaling, and the pace of life in cities. Proc. Natl. Acad. Sci. U. S. A., pages 7301–7306, 2007.
  7. D. Floreano. Bio-inspired artificial intelligence: Theories, methods, and technologies. MIT Press, 255 Main St., NE18, Fl. 9, Cambridge, MA 02142, 2008.
  8. Frameworks for collective intelligence: A systematic literature review. ACM Comput. Surv., 53:14:1–14:36, 2 2020.
  9. The computational beauty of flocking: boids revisited. Math. Comput. Model. Dyn. Syst., 13:331–347, 8 2007.
  10. Novel type of phase transition in a system of self-driven particles. Phys. Rev. Lett., 75:1226–1229, 8 1995.
  11. Evolutionary dynamics of collective action in n-person stag hunt dilemmas. Proc. R. Soc. B, 276:315, 1 2009.
  12. M. Perc and P. Grigolini. Collective behavior and evolutionary games — an introduction. Chaos Solitons Fractals, 56:1–5, 11 2013.
  13. R. Bellman. The theory of dynamic programming. Bull. Am. Math. Soc., 60:503–515, 7 1954.
  14. Reinforcement learning algorithm for non-stationary environments. Appl. Intell., 50:3590–3606, 11 2020.
  15. Flocking behaviour in simple ecosystems as a result of artificial evolution. Appl. Soft Comput., 11:982–990, 1 2011.
  16. Evolving flocking in embodied agents based on local and global application of reynolds’ rules. PLoS One, 14:e0224376, 10 2019.
  17. Intrinsically motivated collective motion. Proc. Natl. Acad. Sci. U. S. A., 116:15362–15367, 7 2019.
  18. J. H. Holland. Adaptation in natural and artificial systems: An introductory analysis with applications to biology, control, and artificial intelligence, volume 1. MIT Press, 255 Main St., NE18, Fl. 9, Cambridge, MA 02142, 1998.
  19. M. Dorigo and G. Di Caro. Ant colony optimization: A new meta-heuristic. Proc. Congr. Evol. Comput. (CEC), 2:1470–1477, 1999.
  20. Deep learning. Nature, 521:436–444, 5 2015.
  21. W. D. Hamilton. Geometry for the selfish herd. J. Theor. Biol., 31:295–311, 5 1971.
  22. C. P. van Schaik. Why are diurnal primates living in groups? Behaviour, 87:120–144, 1983.
  23. G. Packer and L. Ruttan. The evolution of cooperative hunting. Am. Nat., 132:159–198, 1988.
  24. Effective leadership and decision-making in animal groups on the move. Nature, 433:513–516, 2 2005.
  25. B. Majolo and P. Huang. Group living, volume 1. Springer, Cham, Gewerbestrasse 11, Cham, CH-6330, Switzerland, 2022.
  26. A. R. Barron. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. Inf. Theory, 39:930–945, 1993.
  27. Y. Bengio and Y. LeCun. Scaling learning algorithms towards AI. In L. Bottou, O. Chapelle, D. DeCoste, & J. Weston (Eds.), Large-scale kernel machines, volume 1. MIT Press, 255 Main St., NE18, Fl. 9, Cambridge, MA 02142, 2007.
  28. F. Rosenblatt. The perceptron: A probabilistic model for information storage and organization in the brain. Psychol. Rev., 65:386–408, 11 1958.
  29. G. Cybenko. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems, 2:303–314, 12 1989.
  30. C. R. daCunha. Machine learning for the physical sciences: Fundamentals and prototyping with Julia, volume 1. CRC Press, 2385 NW Executive Center Dr., Ste. 320, Boca Raton, FL 33431, 12 2023.
  31. Comparative cognition: Experimental explorations of animal intelligence. Comp. Cogn. Exp. Explor. Anim. Intell., pages 1–720, 3 2009.
  32. Cell learning. Curr. Biol., 28:R1180–R1184, 2018.
  33. A novel method for investigating the collective behaviour of fish: Introducing ’robofish’. Behav. Ecol. Sociobiol., 64:1211–1218, 6 2010.
  34. Inferring the rules of interaction of shoaling fish. Proc. Natl. Acad. Sci. U. S. A., 108:18726–18731, 11 2011.
  35. Statistical mechanics for natural flocks of birds. Proc. Natl. Acad. Sci. U. S. A., 109:4786–4791, 3 2012.
  36. Deciphering interactions in moving animal groups. PLoS Comput. Biol., 8:e1002678, 2012.
  37. Interaction ruling animal collective behavior depends on topological rather than metric distance: Evidence from a field study. Proc. Natl. Acad. Sci. U. S. A., 105:1232–1237, 1 2008.
  38. A. Costanzo and C. K. Hemelrijk. Spontaneous emergence of milling (vortex state) in a vicsek-like model. J. Phys. D Appl. Phys., 51:134004, 3 2018.
  39. N. Wiener. Differential-space. J. Math. Phys., 2:131–174, 10 1923.
  40. A. Genthon. The concept of velocity in the history of brownian motion – from physics to mathematics and vice versa. Eur. Phys. J. H, 45:49–105, 6 2020.
  41. C. R. daCunha. Introduction to econophysics: Contemporary approaches with Python simulations, volume 1. CRC Press, 6000 Broken Sound Parkway NW, Ste. 300, Boca Raton, FL 33487-2742, 2022.
  42. A. Lipowski and D. Lipowska. Roulette-wheel selection via stochastic acceptance. Physica A, 391:2193–2196, 3 2012.
  43. X. Yao. Evolving artificial neural networks. Proc. IEEE, 87:1423–1447, 1999.
  44. L. Ubbelohde. The principle of the suspended level: Applications to the measurement of viscosity and other properties of liquids. Ind. Eng. Chem. Anal. Ed., 9:85–90, 2 1937.
  45. Julia: A fresh approach to numerical computing. SIAM Rev., 59(1):65–98, 2017.
  46. I. Giardina. Collective behavior in animal groups: Theoretical models and empirical studies. HFSP J., 2:205–219, 8 2008.
  47. Collective memory and spatial sorting in animal groups. J. Theor. Biol., 218:1–11, 2002.
  48. S. Kullback and R. A. Leibler. On information and sufficiency. Ann. Math. Stat., 22(1):79–86, 1951.
  49. The mechanism of stochastic resonance. J. Phys. A Math. Gen., 14:L453, 1981.
  50. Chain reaction of ideas: Can radioactive decay predict technological innovation? Physica A, 654:130132, 11 2024.
  51. W. Sutherland. The viscosity of gases and molecular force. Philos. Mag., 36:507–531, 1893.
  52. G. A. Bird. Molecular gas dynamics and the direct simulation of gas flows, volume 42 of Oxford Eng. Sci. Ser. Clarendon Press, Oxford and New York, 1994.
  53. K. Matsumoto and I. Tsuda. Noise-induced order. J. Stat. Phys., 31:87–106, 4 1983.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets