Mutual Information As a Task-Independent Utility Function for Evolutionary Robotics

  • Valerio Sperati
  • Vito Trianni
  • Stefano Nolfi
Part of the Emergence, Complexity and Computation book series (ECC, volume 9)


The design of the control system for a swarm of robots is not a trivial enterprise. Above all, it is difficult to define which are the individual rules that produce a desired swarm behaviour without an a priori knowledge of the system features. For this reason, evolutionary or learning processes have been widely used to automatically synthesise group behaviours (see, for instance, Matarić 1997; Quinn et al. 2003; Baldassarre et al. 2007). In this paper, we investigate the use of information-theoretic concepts such as entropy and mutual information as task-independent utility functions for mobile robots, which adapt on the basis of an evolutionary or learning process. We believe that the use of implicit and general purpose utility functions—fitness functions or reward/error measures—can allow evolution or learning to explore the search space more freely, without being constrained by an explicit description of the desired solution. In this way, it is possible to discover behavioural and cognitive skills that play useful functionalities, and that might be hard to identify beforehand by the experimenter without an a priori knowledge of the system under study. Such task-independent utility functions can be conceived as universal intrinsic drives toward the development of useful behaviours in adaptive embodied agents.


Mutual Information Motor State Light Bulb Average Mutual Information Online Supplementary Material 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Baldassarre, G., Trianni, V., Bonani, M., Mondada, F., Dorigo, M., Nolfi, S.: Self-organised coordinated motion in groups of physically connected robots. IEEE Transactions on Systems, Man and Cybernetics - Part B: Cybernetics 37(1), 224–239 (2007)CrossRefGoogle Scholar
  2. Brenner, N., Bialek, W., de Ruyter van Steveninck, R.: Adaptive rescaling maximizes information transmission. Neuron 26, 695–702 (2000)CrossRefGoogle Scholar
  3. Capdepuy, P., Polani, D., Nehaniv, C.: Maximization of potential information flow as a universal utility for collective behaviour. In: Proceedings of the 2007 IEEE Symposium on Artificial Life (CI-ALife 2007), pp. 207–213. IEEE Press, Piscataway (2007)CrossRefGoogle Scholar
  4. Cianci, C.M., Raemy, X., Pugh, J., Martinoli, A.: Communication in a swarm of miniature robots: The e-puck as an educational tool for swarm robotics. In: Şahin, E., Spears, W.M., Winfield, A.F.T. (eds.) SAB 2006 Ws 2007. LNCS, vol. 4433, pp. 103–115. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  5. Feldman, D.: A brief introduction to: Information theory, excess entropy and computational mechanics. Technical report, College of the Atlantic, Bar Harbor, ME (2002)Google Scholar
  6. Funes, P., Orme, B., Bonabeau, E.: Evolving emergent group behaviors for simple humans agents. In: Banzhaf, W., Christaller, T., Dittrich, P., Kim, J.T., Ziegler, J. (eds.) ECAL 2003. LNCS (LNAI), vol. 2801, pp. 76–89. Springer, Heidelberg (2003)Google Scholar
  7. Harder, M., Polani, D., Nehaniv, C.: Two agents acting as one. In: Proc. of the Alife XII Conference (2010)Google Scholar
  8. Harder, M., Polani, D., Nehaniv, C.: Think globally, sense locally: From local information to global features. In: IEEE Symposium on Artificial Life (2011)Google Scholar
  9. Jakobi, N.: Evolutionary robotics and the radical envelope of noise hypothesis. Adaptive Behavior 6, 325–368 (1997)CrossRefGoogle Scholar
  10. Jung, T., Polani, D., Stone, P.: Empowerment for continuous agent-environment systems. Adaptive Behavior 19, 16–39 (2011)CrossRefGoogle Scholar
  11. Klyubin, A.S., Polani, D., Nehaniv, C.L.: All else being equal be empowered. In: Capcarrère, M.S., Freitas, A.A., Bentley, P.J., Johnson, C.G., Timmis, J. (eds.) ECAL 2005. LNCS (LNAI), vol. 3630, pp. 744–753. Springer, Heidelberg (2005a)CrossRefGoogle Scholar
  12. Klyubin, A., Polani, D., Nehaniv, C.: Empowerment: A universal agent-centric measure of control. In: Proceedings of the 2005 IEEE Congress on Evolutionary Computation, pp. 128–135. IEEE Press, Piscataway (2005b)CrossRefGoogle Scholar
  13. Klyubin, A., Polani, D., Nehaniv, C.: Keep your options open: An information-based driving principle for sensorimotor systems. PLoS ONE 3(12) (2008)Google Scholar
  14. Lizier, J., Prokopenko, M., Tanev, I., Zomaya, A.: Emergence of glider-like structures in a modular robotic system. In: Proc. Eleventh International Conference on the Simulation and Synthesis of Living Systems (ALife XI), pp. 366–373 (2008)Google Scholar
  15. Lungarella, M., Pegors, T., Bulwinkle, D., Sporns, O.: Methods for quantifying the information structure of sensory and motor data. Neuroinformatics 3(3), 243–262 (2005)CrossRefGoogle Scholar
  16. Lungarella, M., Pfeifer, R.: Robots as cognitive tools: Information theoretic analysis of sensory-motor data. In: Proceedings of the 2nd International IEEE/RSJ Conference on Humanoid Robotics, pp. 245–252. IEEE Press, Piscataway (2001)Google Scholar
  17. Lungarella, M., Sporns, O.: Information self-structuring: Key principle for learning and development. In: Proceedings of the 4th International Conference on Development and Learning, pp. 25–30. IEEE Press, Piscataway (2005)Google Scholar
  18. Matarić, M.: Learning social behavior. Robotics and Autonomous Systems 20, 191–204 (1997)CrossRefGoogle Scholar
  19. Miglino, O., Lund, H., Nolfi, S.: Evolving mobile robots in simulated and real environments. Artificial Life 2(4), 417–434 (1995)CrossRefGoogle Scholar
  20. Mondada, F., Bonani, M.: The e-puck education robot (2007),
  21. Nolfi, S., Floreano, D.: Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines. MIT Press/Bradford Books, Cambridge, MA (2000)Google Scholar
  22. Olsson, L., Nehaniv, C., Polani, D.: Sensor adaptation and development in robots by entropy maximization of sensory data. In: Proceedings of the 6th IEEE International Symposium on Computational Intelligence in Robotics and Automation (CIRA 2005), pp. 587–592. IEEE Computer Society Press, Piscataway (2005)CrossRefGoogle Scholar
  23. Prokopenko, M., Gerasimov, V., Tanev, I.: Evolving spatiotemporal coordination in a modular robotic system. In: Nolfi, S., Baldassarre, G., Calabretta, R., Hallam, J.C.T., Marocco, D., Meyer, J.-A., Miglino, O., Parisi, D. (eds.) SAB 2006. LNCS (LNAI), vol. 4095, pp. 558–569. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  24. Prokopenko, M., Wang, P.: Evaluating team performance at the edge of chaos. In: Polani, D., Browning, B., Bonarini, A., Yoshida, K. (eds.) RoboCup 2003. LNCS (LNAI), vol. 3020, pp. 89–101. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  25. Quinn, M., Smith, L., Mayley, G., Husbands, P.: Evolving controllers for a homogeneous system of physical robots: Structured cooperation with minimal sensors. Philosophical Transactions of the Royal Society of London, Series A: Mathematical, Physical and Engineering Sciences 361, 2321–2344 (2003)MathSciNetCrossRefGoogle Scholar
  26. Salge, C., Polani, D.: Local information maximisation creates emergent flocking behaviour. In: Advances in Artificial Life, ECAL 2011: Proceedings of the Eleventh European Conference on Artificial Life (2011)Google Scholar
  27. Shannon, C.: A mathematical theory of communication. The Bell System Technical Journal 27, 379–423, 623–656 (1948)Google Scholar
  28. Sperati, V., Trianni, V., Nolfi, S.: Evolving coordinated group behaviours through maximisation of mean mutual information. Swarm Intelligence 2(2-4), 73–95 (2008)CrossRefGoogle Scholar
  29. Sperati, V., Trianni, V., Nolfi, S.: Self-organised path formation in a swarm of robots. Swarm Intelligence 5(2), 97–119 (2011)CrossRefGoogle Scholar
  30. Sporns, O., Lungarella, M.: Evolving coordinated behavior by maximizing information structure. In: Rocha, L., Yaeger, L., Bedau, M., Floreano, D., Goldstone, R., Vespignani, A. (eds.) Artificial Life X: Proceedings of the Tenth International Conference on the Simulation and Synthesis of Living Systems, pp. 323–329. MIT Press, Cambridge (2006)Google Scholar
  31. Sporns, O., Tononi, G., Edelman, G.: Connectivity and complexity: the relationship between neuroanatomy and brain dynamics. Neural Networks 13, 909–922 (2000)CrossRefGoogle Scholar
  32. Tarapore, D., Lungarella, M., Gomez, G.: Fingerprinting agent-environment interaction via information theory. In: Groen, F., Amato, N., Bonarini, A., Yoshida, E., Kröse, B. (eds.) Intelligent Autonomous Systems, vol. 8, pp. 512–520. IOS Press, Amsterdam (2004)Google Scholar
  33. Tarapore, D., Lungarella, M., Gomez, G.: Quantifying patterns of agent-environment interaction. Robotics and Autonomous Systems 54(2), 150–158 (2006)CrossRefGoogle Scholar
  34. Tononi, G., Edelman, G., Sporns, O.: Complexity and coherency: integrating information in the brain. Trends in Cognitive Sciences 2(12), 474–484 (1998)CrossRefGoogle Scholar
  35. Tononi, G., Sporns, O., Edelman, G.: A measure for brain complexity: Relating functional segregation and integration in the nervous system. Proceedings of the National Academy of Sciences 91, 5033–5037 (1994)CrossRefGoogle Scholar
  36. Tononi, G., Sporns, O.: G. Edelman, G. A complexity measure for selective matching of signals by the brain. Proceedings of the National Academy of Sciences 93, 3422–3427 (1996)CrossRefGoogle Scholar
  37. Trianni, V., Nolfi, S.: Self-organising sync in a robotic swarm. a dynamical system view. IEEE Transactions on Evolutionary Computation 13(4), 722–741 (2009)CrossRefGoogle Scholar
  38. Trianni, V., Nolfi, S.: chapter Evolving collective control, cooperation and distributed cognition. In: The Handbook of Collective Robotics - Fundamentals and Challenges, pp. 168–189. Pan Stanford Publishing, Singapore (2012)Google Scholar
  39. Trianni, V., Nolfi, S., Dorigo, M.: Evolution, self-organisation and swarm robotics. In: Blum, C., Merkle, D. (eds.) Swarm Intelligence. Introduction and Applications. Natural Computing Series. Springer, Berlin (2008)Google Scholar
  40. Van Dyke Parunak, H., Brueckner, S.: Entropy and self-organization in multi-agent systems. In: Proceedings of the Fifth International Conference on Autonomous Agents, pp. 124–130. ACM Press, New York (2001)CrossRefGoogle Scholar
  41. Wang, X., Miller, J., Lizier, J., Prokopenko, M., Rossi, L.: Measuring information storage and transfer in swarms. In: Proc. Eleventh European Conference on the Synthesis and Simulation of Living Systems (ECAL 2011), pp. 838–845 (2011)Google Scholar
  42. Zahedi, K., Ay, N., Der, R.: Higher coordination with less control - a result of information maximization in the sensorimotor loop. Adaptive Behavior 18, 338–355 (2010)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Valerio Sperati
    • 1
  • Vito Trianni
    • 1
  • Stefano Nolfi
    • 1
  1. 1.Laboratory of Autonomous Robotics and Artificial LifeInstitute of Cognitive Sciences and Technologies, CNRRomeItaly

Personalised recommendations