اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدMassive Multi-Agent Data-Driven Simulations of the GitHub Ecosystem
290
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Simulating and predicting planetary-scale techno-social systems poses heavy computational and modeling challenges. The DARPA SocialSim program set the challenge to model the evolution of GitHub, a large collaborative software-development ecosystem, using massive multi-agent simulations. We describe our best performing models and our agent-based simulation framework, which we are currently extending to allow simulating other planetary-scale techno-social systems. The challenge problem measured participants ability, given 30 months of meta-data on user activity on GitHub, to predict the next months activity as measured by a broad range of metrics applied to ground truth, using agent-based simulation. The challenge required scaling to a simulation of roughly 3 million agents producing a combined 30 million actions, acting on 6 million repositories with commodity hardware. It was also important to use the data optimally to predict the agents next moves. We describe the agent framework and the data analysis employed by one of the winning teams in the challenge. Six different agent models were tested based on a variety of machine learning and statistical methods. While no single method proved the most accurate on every metric, the broadly most successful sampled from a stationary probability distribution of actions and repositories for each agent. Two reasons for the success of these agents were their use of a distinct characterization of each agent, and that GitHub users change their behavior relatively slowly.
قيم البحث
اقرأ أيضاً
Trajectory interpolation, the process of filling-in the gaps and removing noise from observed agent trajectories, is an essential task for the motion inference in multi-agent setting. A desired trajectory interpolation method should be robust to nois
e, changes in environments or agent densities, while also being yielding realistic group movement behaviors. Such realistic behaviors are, however, challenging to model as they require avoidance of agent-agent or agent-environment collisions and, at the same time, seek computational efficiency. In this paper, we propose a novel framework composed of data-driven priors (local, global or combined) and an efficient optimization strategy for multi-agent trajectory interpolation. The data-driven priors implicitly encode the dependencies of movements of multiple agents and the collision-avoiding desiderata, enabling elimination of costly pairwise collision constraints and resulting in reduced computational complexity and often improved estimation. Various combinations of priors and optimization algorithms are evaluated in comprehensive simulated experiments. Our experimental results reveal important insights, including the significance of the global flow prior and the lesser-than-expected influence of data-driven collision priors.
Activity-based models, as a specific instance of agent-based models, deal with agents that structure their activity in terms of (daily) activity schedules. An activity schedule consists of a sequence of activity instances, each with its assigned star
t time, duration and location, together with transport modes used for travel between subsequent activity locations. A critical step in the development of simulation models is validation. Despite the growing importance of activity-based models in modelling transport and mobility, there has been so far no work focusing specifically on statistical validation of such models. In this paper, we propose a six-step Validation Framework for Activity-based Models (VALFRAM) that allows exploiting historical real-world data to assess the validity of activity-based models. The framework compares temporal and spatial properties and the structure of activity schedules against real-world travel diaries and origin-destination matrices. We confirm the usefulness of the framework on three real-world activity-based transport models.
Simulation of population dynamics is a central research theme in computational biology, which contributes to understanding the interactions between predators and preys. Conventional mathematical tools of this theme, however, are incapable of accounti
ng for several important attributes of such systems, such as the intelligent and adaptive behavior exhibited by individual agents. This unrealistic setting is often insufficient to simulate properties of population dynamics found in the real-world. In this work, we leverage multi-agent deep reinforcement learning, and we propose a new model of large-scale predator-prey ecosystems. Using different variants of our proposed environment, we show that multi-agent simulations can exhibit key real-world dynamical properties. To obtain this behavior, we firstly define a mating mechanism such that existing agents reproduce new individuals bound by the conditions of the environment. Furthermore, we incorporate a real-time evolutionary algorithm and show that reinforcement learning enhances the evolution of the agents physical properties such as speed, attack and resilience against attacks.
We propose a curriculum-driven learning strategy for solving difficult multi-agent coordination tasks. Our method is inspired by a study of animal communication, which shows that two straightforward design features (mutual reward and decentralization
) support a vast spectrum of communication protocols in nature. We highlight the importance of similarly interpreting emergent communication as a spectrum. We introduce a toroidal, continuous-space pursuit-evasion environment and show that naive decentralized learning does not perform well. We then propose a novel curriculum-driven strategy for multi-agent learning. Experiments with pursuit-evasion show that our approach enables decentralized pursuers to learn to coordinate and capture a superior evader, significantly outperforming sophisticated analytical policies. We argue through additional quantitative analysis -- including influence-based measures such as Instantaneous Coordination -- that emergent implicit communication plays a large role in enabling superior levels of coordination.
Collective or group intelligence is manifested in the fact that a team of cooperating agents can solve problems more efficiently than when those agents work in isolation. Although cooperation is, in general, a successful problem solving strategy, it
is not clear whether it merely speeds up the time to find the solution, or whether it alters qualitatively the statistical signature of the search for the solution. Here we review and offer insights on two agent-based models of distributed cooperative problem-solving systems, whose task is to solve a cryptarithmetic puzzle. The first model is the imitative learning search in which the agents exchange information on the quality of their partial solutions to the puzzle and imitate the most successful agent in the group. This scenario predicts a very poor performance in the case imitation is too frequent or the group is too large, a phenomenon akin to Groupthink of social psychology. The second model is the blackboard organization in which agents read and post hints on a public blackboard. This brainstorming scenario performs the best when there is a stringent limit to the amount of information that is exhibited on the board. Both cooperative scenarios produce a substantial speed up of the time to solve the puzzle as compared with the situation where the agents work in isolation. The statistical signature of the search, however, is the same as that of the independent search.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
