Abstract
Complex global behavior patterns can emerge from very simple local interactions between many agents. However, no local interaction rules have been identified that generate some patterns observed in nature, for example the rotating balls, rotating tornadoes and the full-core rotating mills observed in fish collectives. Here we show that locally interacting agents modelled with a minimal cognitive system can produce these collective patterns. We obtained this result by using recent advances in reinforcement learning to systematically solve the inverse modelling problem: given an observed collective behavior, we automatically find a policy generating it. Our agents are modelled as processing the information from neighbour agents to choose actions with a neural network and move in an environment of simulated physics. Even though every agent is equipped with its own neural network, all agents have the same network architecture and parameter values, ensuring in this way that a single policy is responsible for the emergence of a given pattern. We find the final policies by tuning the neural network weights until the produced collective behaviour approaches the desired one. By using modular neural networks with modules using a small number of inputs and outputs, we built an interpretable model of collective motion. This enabled us to analyse the policies obtained. We found a similar general structure for the four different collective patterns, not dissimilar to the one we have previously inferred from experimental zebrafish trajectories; but we also found consistent differences between policies generating the different collective pattern, for example, repulsion in the vertical direction for the more three-dimensional structures of the sphere and tornado. Our results illustrate how new advances in artificial intelligence, and specifically in reinforcement learning, allow new approaches to analysis and modelling of collective behavior.
Highlights
Complex collective phenomena can emerge from simple local interactions of agents who lack the ability to understand or directly control the collective [1,2,3,4,5,6,7,8,9,10,11,12,13,14]
As in previous work [44], we enabled interpretability by using a neural network built from two modules with a few inputs and few outputs each, Figure 2
The second part consists in sampling each parameter, p1,i, p2,i, p3,i, from a clipped Gaussian distribution with the mean and variance given by the outputs of the first part, Figure 2B
Summary
Complex collective phenomena can emerge from simple local interactions of agents who lack the ability to understand or directly control the collective [1,2,3,4,5,6,7,8,9,10,11,12,13,14]. Researchers have relied on the heuristic known as the modeling cycle. The researcher first proposes a set of candidate local rules based on some knowledge of the sensory and motor capabilities of the agents. The rules are numerically simulated and the results compared with the desired outcome. This cycle is repeated, subsequently changing the rules until an adequate match between simulated trajectories and the target collective configuration is found
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
