ترغب بنشر مسار تعليمي؟ اضغط هنا

Towards a Very Large Scale Traffic Simulator for Multi-Agent Reinforcement Learning Testbeds

283   0   0.0 ( 0 )
 نشر من قبل Zijian Hu
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Smart traffic control and management become an emerging application for Deep Reinforcement Learning (DRL) to solve traffic congestion problems in urban networks. Different traffic control and management policies can be tested on the traffic simulation. Current DRL-based studies are mainly supported by the microscopic simulation software (e.g., SUMO), while it is not suitable for city-wide control due to the computational burden and gridlock effect. To the best of our knowledge, there is a lack of studies on the large-scale traffic simulator for DRL testbeds, which could further hinder the development of DRL. In view of this, we propose a meso-macro traffic simulator for very large-scale DRL scenarios. The proposed simulator integrates mesoscopic and macroscopic traffic simulation models to improve efficiency and eliminate gridlocks. The mesoscopic link model simulates flow dynamics on roads, and the macroscopic Bathtub model depicts vehicle movement in regions. Moreover, both types of models can be hybridized to accommodate various DRL tasks. This creates portals for mixed transportation applications under different contexts. The result shows that the developed simulator only takes 46 seconds to finish a 24-hour simulation in a very large city with 2.2 million vehicles, which is much faster than SUMO. Additionally, we develop a graphic interface for users to visualize the simulation results in a web explorer. In the future, the developed meso-macro traffic simulator could serve as a new environment for very large-scale DRL problems.



قيم البحث

اقرأ أيضاً

96 - Yanan Wang , Tong Xu , Xin Niu 2019
The development of intelligent traffic light control systems is essential for smart transportation management. While some efforts have been made to optimize the use of individual traffic lights in an isolated way, related studies have largely ignored the fact that the use of multi-intersection traffic lights is spatially influenced and there is a temporal dependency of historical traffic status for current traffic light control. To that end, in this paper, we propose a novel SpatioTemporal Multi-Agent Reinforcement Learning (STMARL) framework for effectively capturing the spatio-temporal dependency of multiple related traffic lights and control these traffic lights in a coordinating way. Specifically, we first construct the traffic light adjacency graph based on the spatial structure among traffic lights. Then, historical traffic records will be integrated with current traffic status via Recurrent Neural Network structure. Moreover, based on the temporally-dependent traffic information, we design a Graph Neural Network based model to represent relationships among multiple traffic lights, and the decision for each traffic light will be made in a distributed way by the deep Q-learning method. Finally, the experimental results on both synthetic and real-world data have demonstrated the effectiveness of our STMARL framework, which also provides an insightful understanding of the influence mechanism among multi-intersection traffic lights.
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.
Cooperative multi-agent reinforcement learning often requires decentralised policies, which severely limit the agents ability to coordinate their behaviour. In this paper, we show that common knowledge between agents allows for complex decentralised coordination. Common knowledge arises naturally in a large number of decentralised cooperative multi-agent tasks, for example, when agents can reconstruct parts of each others observations. Since agents an independently agree on their common knowledge, they can execute complex coordinated policies that condition on this knowledge in a fully decentralised fashion. We propose multi-agent common knowledge reinforcement learning (MACKRL), a novel stochastic actor-critic algorithm that learns a hierarchical policy tree. Higher levels in the hierarchy coordinate groups of agents by conditioning on their common knowledge, or delegate to lower levels with smaller subgroups but potentially richer common knowledge. The entire policy tree can be executed in a fully decentralised fashion. As the lowest policy tree level consists of independent policies for each agent, MACKRL reduces to independently learnt decentralised policies as a special case. We demonstrate that our method can exploit common knowledge for superior performance on complex decentralised coordination tasks, including a stochastic matrix game and challenging problems in StarCraft II unit micromanagement.
Agent advising is one of the main approaches to improve agent learning performance by enabling agents to share advice. Existing advising methods have a common limitation that an adviser agent can offer advice to an advisee agent only if the advice is created in the same state as the advisees concerned state. However, in complex environments, it is a very strong requirement that two states are the same, because a state may consist of multiple dimensions and two states being the same means that all these dimensions in the two states are correspondingly identical. Therefore, this requirement may limit the applicability of existing advising methods to complex environments. In this paper, inspired by the differential privacy scheme, we propose a differential advising method which relaxes this requirement by enabling agents to use advice in a state even if the advice is created in a slightly different state. Compared with existing methods, agents using the proposed method have more opportunity to take advice from others. This paper is the first to adopt the concept of differential privacy on advising to improve agent learning performance instead of addressing security issues. The experimental results demonstrate that the proposed method is more efficient in complex environments than existing methods.
We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn such comm unication without centralized training of agents, due in part to a difficult joint exploration problem. We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem. We also apply our methods to a more extended environment, showing that agents with these inductive biases achieve better performance, and analyse the resulting communication protocols.
التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا