Abstract
This paper examines whether and how a primitive form of communication emerges between adaptive agents by using their excess degrees of freedom in action and perception. As a case study, we consider a game in which two reinforcement learning agents learn to earn rewards by intruding into the other’s territory. Our simulation shows that agents with lights and light sensors can learn turn-taking behavior for avoiding collisions using visual communication. Further analysis reveals a variety in the mapping of messages to signals. In some cases, the differentiation of roles into a sender and a receiver was observed. The result confirmed that protocommunication can emerge through interaction between agents having generic reinforcement learning capability.
Similar content being viewed by others
References
Kaneko K, Tsuda I (2000) Complex systems: chaos and beyond. A constructive approach with applications in life sciences. Springer, Berlin
Cangelosi A, Parisi D (1998) The emergence of a language in an evolving population of neural networks. Connection Sci 10(2): 83–97
Marocco D, Nolfi S (2004) Emergence of communication in embodied agents: co-adapting communicative and non-communicative behaviours. In: Cangelosi A et al. (eds) Proceedings of the 9th Neural Computation and Psychology Workshop, Plymouth, Sep. 8–10, 2004, World Scientific, Singapore
Steels L, Vogt P (1997) Grounding adaptive language games in robotic agents. In: Husbands C, Harvey I (eds) Proceedings of the 4th European Conference on Artificial Life (ECAL’ 97), MIT Press, Cambridge, pp 474–482
Tensho S, Maekawa S, Yoshimoto J, et al. (2005) Gradual emergence of communication in a multi-agent environment. Proceedings of the 10th International Symposium on Artificial Life and Robotics (AROB 10), Beppu, Oita, Japan, Feb. 4–6, 2005, pp 551–554
Sutton RS, Barto AG (1998) Reinforcement learning. MIT Press, Cambridge
Halliday TR, Slater PJB (1983) Animal behavior. Blackwell Scientific, Oxford
Tomasello M (1999) The cultural origins of human cognition. Harvard University Press, Cambridge
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Sato, T., Uchibe, E. & Doya, K. Learning how, what, and whether to communicate: emergence of protocommunication in reinforcement learning agents. Artif Life Robotics 12, 70–74 (2008). https://doi.org/10.1007/s10015-007-0444-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10015-007-0444-x