Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly acc...Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.展开更多
Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well wi...Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex problems.Given the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.展开更多
Generative adversarial imitation learning(GAIL)directly imitates the behavior of experts from human demonstration instead of designing explicit reward signals like reinforcement learning.Meanwhile,GAIL overcomes the d...Generative adversarial imitation learning(GAIL)directly imitates the behavior of experts from human demonstration instead of designing explicit reward signals like reinforcement learning.Meanwhile,GAIL overcomes the defects of traditional imitation learning by using a generative adversary network framework and shows excellent performance in many fields.However,GAIL directly acts on immediate rewards,a feature that is reflected in the value function after a period of accumulation.Thus,when faced with complex practical problems,the learning efficiency of GAIL is often extremely low and the policy may be slow to learn.One way to solve this problem is to directly guide the action(policy)in the agents'learning process,such as the control sharing(CS)method.This paper combines reinforcement learning and imitation learning and proposes a novel GAIL framework called generative adversarial imitation learning based on control sharing policy(GACS).GACS learns model constraints from expert samples and uses adversarial networks to guide learning directly.The actions are produced by adversarial networks and are used to optimize the policy and effectively improve learning efficiency.Experiments in the autonomous driving environment and the real-time strategy game breakout show that GACS has better generalization capabilities,more efficient imitation of the behavior of experts,and can learn better policies relative to other frameworks.展开更多
文摘Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed,equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties,performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance.Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.
基金supported by the Open Project of Xiangjiang Laboratory (22XJ02003)Scientific Project of the National University of Defense Technology (NUDT)(ZK21-07, 23-ZZCX-JDZ-28)+1 种基金the National Science Fund for Outstanding Young Scholars (62122093)the National Natural Science Foundation of China (72071205)。
文摘Traditional expert-designed branching rules in branch-and-bound(B&B) are static, often failing to adapt to diverse and evolving problem instances. Crafting these rules is labor-intensive, and may not scale well with complex problems.Given the frequent need to solve varied combinatorial optimization problems, leveraging statistical learning to auto-tune B&B algorithms for specific problem classes becomes attractive. This paper proposes a graph pointer network model to learn the branch rules. Graph features, global features and historical features are designated to represent the solver state. The graph neural network processes graph features, while the pointer mechanism assimilates the global and historical features to finally determine the variable on which to branch. The model is trained to imitate the expert strong branching rule by a tailored top-k Kullback-Leibler divergence loss function. Experiments on a series of benchmark problems demonstrate that the proposed approach significantly outperforms the widely used expert-designed branching rules. It also outperforms state-of-the-art machine-learning-based branch-and-bound methods in terms of solving speed and search tree size on all the test instances. In addition, the model can generalize to unseen instances and scale to larger instances.
基金Supported in Part by the National Natural Science Foundation of China (U1808206)。
文摘Generative adversarial imitation learning(GAIL)directly imitates the behavior of experts from human demonstration instead of designing explicit reward signals like reinforcement learning.Meanwhile,GAIL overcomes the defects of traditional imitation learning by using a generative adversary network framework and shows excellent performance in many fields.However,GAIL directly acts on immediate rewards,a feature that is reflected in the value function after a period of accumulation.Thus,when faced with complex practical problems,the learning efficiency of GAIL is often extremely low and the policy may be slow to learn.One way to solve this problem is to directly guide the action(policy)in the agents'learning process,such as the control sharing(CS)method.This paper combines reinforcement learning and imitation learning and proposes a novel GAIL framework called generative adversarial imitation learning based on control sharing policy(GACS).GACS learns model constraints from expert samples and uses adversarial networks to guide learning directly.The actions are produced by adversarial networks and are used to optimize the policy and effectively improve learning efficiency.Experiments in the autonomous driving environment and the real-time strategy game breakout show that GACS has better generalization capabilities,more efficient imitation of the behavior of experts,and can learn better policies relative to other frameworks.
