While most research focuses on the state-action function part through reducing the bootstrapping error in value function approximation induced by the distribution shift of training data, the effects of error propagation in generative modeling have been neglected.
Traffic simulators act as an essential component in the operating and planning of transportation systems.
Historical features are important in ads click-through rate (CTR) prediction, because they account for past engagements between users and ads.
When a new task is encountered, it constructs a meta-knowledge pathway by either utilizing the most relevant knowledge blocks or exploring new blocks.
Moreover, both MetaMix and Channel Shuffle outperform state-of-the-art results by a large margin across many datasets and are compatible with existing meta-learning algorithms.
To the best of our knowledge, we are the first to learn to model the state transition of moving agents with system dynamics.
Moreover, learning important spatial patterns in offline retail is challenging due to the scarcity of data and the high cost of exploration and experimentation in the physical world.
In order to efficiently learn with small amount of data on new tasks, meta-learning transfers knowledge learned from previous tasks to the new ones.
Knowledge graphs (KGs) serve as useful resources for various natural language processing applications.
Towards the challenging problem of semi-supervised node classification, there have been extensive studies.
In the face of growing needs for water and energy, a fundamental understanding of the environmental impacts of human activities becomes critical for managing water and energy resources, remedying water pollution, and making regulatory policy wisely.
In order to learn quickly with few samples, meta-learning utilizes prior knowledge learned from previous tasks.
The most commonly used open-source traffic simulator SUMO is, however, not scalable to large road network and large traffic flow, which hinders the study of reinforcement learning on traffic scenarios.
Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions.
In this paper, we propose to re-examine the RL approaches through the lens of classic transportation theory.
To enable cooperation of traffic signals, in this paper, we propose a model, CoLight, which uses graph attentional networks to facilitate communication.
Traffic signal control is an important and challenging real-world problem, which aims to minimize the travel time of vehicles by coordinating their movements at the road intersections.
Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm.
Although both factors have been considered in modeling, existing works make strong assumptions about spatial dependence and temporal dynamics, i. e., spatial dependence is stationary in time, and temporal dynamics is strictly periodical.
Traditional demand prediction methods mostly rely on time series forecasting techniques, which fail to model the complex non-linear spatial and temporal relations.
The increased availability of large-scale trajectory data around the world provides rich information for the study of urban dynamics.