Abstract
While groups where members communicate with each other may perform better than groups without communication, there are multiple scenarios where communication between group members is not possible. Our work analyses the impact of task complexity on individuals and groups of different sizes while solving a goal-seeking navigation task without communication. Our major goal is to determine the effect of task complexity on performance and whether agents in a group are able to coordinate to perform the task effectively despite the lack of communication. We developed a cognitive model of each individual agent that performs the task. We compare the performance of this agent with individual human performance, who worked on the same task. We observe that the cognitive agent is able to replicate the general behavioral trends observed in humans. Using this cognitive model, we generate groups of different sizes where individual agents work in the same goal-seeking task independently and without communication. First, we observe that increasing task complexity by design does not necessarily lead to worse performance in individuals and groups. We also observe that larger groups perform better than smaller groups and individuals alone. However, individual agents within a group perform worse than an agent working on the task alone. This effect is not the result of agents within a group covering less ground in the task compared to individuals alone. Rather, it is an effect resulting from the overlap of the agents within a group. Importantly, agents learn to reduce their overlap and improve their performance without explicit communication. These results can inform the design of AI agents in human-machine teams.
A. Gulati–Currently at the ELLIS Unit Alicante Foundation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anderson, J.R., Lebiere, C.J.: The Atomic Components of Thought. Psychology Press (2014)
Bansal, G., Nushi, B., Kamar, E., Lasecki, W., Weld, D., Horvitz, E.: Beyond accuracy: the role of mental models in human-AI team performance. In: HCOMP. AAAI, October 2019. https://www.microsoft.com/en-us/research/publication/beyond-accuracy-the-role-of-mental-models-in-human-ai-team-performance/
Becker, M., Blatt, F., Szczerbicka, H.: A multi-agent flooding algorithm for search and rescue operations in unknown terrain. In: Klusch, M., Thimm, M., Paprzycki, M. (eds.) MATES 2013. LNCS (LNAI), vol. 8076, pp. 19–28. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-40776-5_5
Botvinick, M., Ritter, S., Wang, J.X., Kurth-Nelson, Z., Blundell, C., Hassabis, D.: Reinforcement learning, fast and slow. Trends Cogn. Sci. 23(5), 408–422 (2019). https://doi.org/10.1016/j.tics.2019.02.006
Dutt, V., Ahn, Y.-S., Gonzalez, C.: Cyber situation awareness: modeling the security analyst in a cyber-attack scenario through instance-based learning. In: Li, Y. (ed.) DBSec 2011. LNCS, vol. 6818, pp. 280–292. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-22348-8_24
Dutt, V., Gonzalez, C.: The role of inertia in modeling decisions from experience with instance-based learning. Front. Psychol. 3, 177 (2012). https://doi.org/10.3389/fpsyg.2012.00177. https://www.frontiersin.org/article/10.3389/fpsyg.2012.00177
Dutt, V., Gonzalez, C.: Accounting for outcome and process measures in dynamic decision-making tasks through model calibration. Technical report, Carnegie Mellon University, Pittsburgh, United States (2015)
Gershman, S.J., Daw, N.D.: Reinforcement learning and episodic memory in humans and animals: an integrative framework. Ann. Rev. Psychol. 68(1), 101–128 (2017). https://doi.org/10.1146/annurev-psych-122414-033625
Gonzalez, C., Ben-Asher, N., Martin, J.M., Dutt, V.: A cognitive model of dynamic cooperation with varied interdependency information. Cogn. Sci. 39(3), 457–495 (2015)
Gonzalez, C., Dutt, V.: Instance-based learning: integrating sampling and repeated decisions from experience. Psychol. Rev. 118(4), 523 (2011)
Gonzalez, C., Dutt, V.: Refuting data aggregation arguments and how the instance-based learning model stands criticism: a reply to Hills and Hertwig. Psychol. Rev. 119(4), 893–898 (2012). https://doi.org/10.1037/a0029445
Gonzalez, C., Lerch, J.F., Lebiere, C.: Instance-based learning in dynamic decision making. Cogn. Sci. 27(4), 591–635 (2003). https://doi.org/10.1207/s15516709cog2704_2. https://onlinelibrary.wiley.com/doi/abs/10.1207/s15516709cog2704_2
Gureckis, T.M., Love, B.C.: Short-term gains, long-term pains: how cues about state aid learning in dynamic environments. Cognition 113(3), 293–313 (2009). https://doi.org/10.1016/j.cognition.2009.03.013
Jensen, E.A.: Dispersion and exploration for robot teams. In: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-Agent Systems, pp. 1437–1438 (2013)
King, A.J., Narraway, C., Hodgson, L., Weatherill, A., Sommer, V., Sumner, S.: Performance of human groups in social foraging: the role of communication in consensus decision making. Biol. Lett. 7(2), 237–240 (2011). https://doi.org/10.1098/rsbl.2010.0808. https://royalsocietypublishing.org/doi/abs/10.1098/rsbl.2010.0808
Lejarraga, T., Lejarraga, J., Gonzalez, C.: Decisions from experience: how groups and individuals adapt to change. Mem. Cogn. 42(8), 1384–1397 (2014). https://doi.org/10.3758/s13421-014-0445-7
McDonald, C., Nguyen, T.N., Gonzalez, C.: Multi-agent specialization and coordination without communication in a gridworld task. In: ACM Collective Intelligence Conference (2021)
Nguyen, T.N., Gonzalez, C.: Cognitive machine theory of mind. In: CogSci (2020)
Nguyen, T.N., Gonzalez, C.: Effects of decision complexity in goal seeking gridworlds: a comparison of instance based learning and reinforcement learning agents. Technical report, Carnegie Mellon University (2020)
Nguyen, T.N., Gonzalez, C.: Minimap: a dynamic decision making interactive tool for search and rescue missions. Technical report, Carnegie Mellon University (2021)
Oesch, N., Dunbar, R.I.M.: Group size, communication, and familiarity effects in foraging human teams. Ethology 124(7), 483–495 (2018). https://doi.org/10.1111/eth.12756. https://onlinelibrary.wiley.com/doi/abs/10.1111/eth.12756
Premack, D., Woodruff, G.: Does the chimpanzee have a theory of mind? Behav. Brain Sci. 1(4), 515–526 (1978). https://doi.org/10.1017/S0140525X00076512
Rabinowitz, N.C., Perbet, F., Song, H.F., Zhang, C., Eslami, S., Botvinick, M.: Machine theory of mind. arXiv preprint arXiv:1802.07740 (2018)
Simon, D., Daw, N.: Environmental statistics and the trade-off between model-based and td learning in humans. In: Shawe-Taylor, J., Zemel, R., Bartlett, P., Pereira, F., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems. vol. 24. Curran Associates, Inc. (2011). https://proceedings.neurips.cc/paper/2011/file/c9e1074f5b3f9fc8ea15d152add07294-Paper.pdf
Sumner, S., King, A.J.: Actions speak louder than words in socially foraging human groups. Commun. Integr. Biol. 4(6), 755–757 (2011). https://doi.org/10.4161/cib.17701. pMID: 22446547
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press (2018)
Acknowledgements
This research was sponsored by the Defense Advanced Research Projects Agency and was accomplished under Grant Number W911NF-20-1-0006.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gulati, A., Nguyen, T.N., Gonzalez, C. (2022). Task Complexity and Performance in Individuals and Groups Without Communication. In: Gurney, N., Sukthankar, G. (eds) Computational Theory of Mind for Human-Machine Teams. AAAI-FSS 2021. Lecture Notes in Computer Science, vol 13775. Springer, Cham. https://doi.org/10.1007/978-3-031-21671-8_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-21671-8_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21670-1
Online ISBN: 978-3-031-21671-8
eBook Packages: Computer ScienceComputer Science (R0)