The theory of“imitation”in painting occupies a leading position in western art,which originated from the theory of“imitation”in ancient Greece,and has become one of the art theories affecting the world through the...The theory of“imitation”in painting occupies a leading position in western art,which originated from the theory of“imitation”in ancient Greece,and has become one of the art theories affecting the world through the continuous development of later generations.Through the exploration of the source of“imitation”in China and the West,there are some comments on the meaning of“imitation”in Chinese classical painting theory,such as“transfer model writing”and“image form”,which is obvious differences from the west.Traditional Chinese painting is a combination of careful observation of natural things and subjective emotions to express their own aesthetic feelings,and ultimately form a vivid artistic conception.Modern imitation is borrowed from Western imitation.In fact,imitation in traditional painting has its own meaning,which contains Chinese aesthetic thought.“Imitation”aesthetics is unique in traditional Chinese painting and is the most important form of painting art.展开更多
UG and imitation are two parallel hypotheses trying to answer how childrens language acquisition is realized. Imitation fails to explain how children acquire language; however, it helps a lot in childrens language acq...UG and imitation are two parallel hypotheses trying to answer how childrens language acquisition is realized. Imitation fails to explain how children acquire language; however, it helps a lot in childrens language acquisition.展开更多
One of the assumptions of previous research in evolutionary game dynamics is that individuals use only one rule to update their strategy. In reality, an individual's strategy update rules may change with the envir...One of the assumptions of previous research in evolutionary game dynamics is that individuals use only one rule to update their strategy. In reality, an individual's strategy update rules may change with the environment, and it is possible for an individual to use two or more rules to update their strategy. We consider the case where an individual updates strategies based on the Moran and imitation processes, and establish mixed stochastic evolutionary game dynamics by combining both processes. Our aim is to study how individuals change strategies based on two update rules and how this affects evolutionary game dynamics. We obtain an analytic expression and properties of the fixation probability and fixation times(the unconditional fixation time or conditional average fixation time) associated with our proposed process. We find unexpected results. The fixation probability within the proposed model is independent of the probabilities that the individual adopts the imitation rule update strategy. This implies that the fixation probability within the proposed model is equal to that from the Moran and imitation processes. The one-third rule holds in the proposed mixed model. However, under weak selection, the fixation times are different from those of the Moran and imitation processes because it is connected with the probability that individuals adopt an imitation update rule. Numerical examples are presented to illustrate the relationships between fixation times and the probability that an individual adopts the imitation update rule, as well as between fixation times and selection intensity. From the simulated analysis, we find that the fixation time for a mixed process is greater than that of the Moran process, but is less than that of the imitation process. Moreover, the fixation times for a cooperator in the proposed process increase as the probability of adopting an imitation update increases; however, the relationship becomes more complex than a linear relationship.展开更多
Mobile Edge Computing(MEC)is promising to alleviate the computation and storage burdens for terminals in wireless networks.The huge energy consumption of MEC servers challenges the establishment of smart cities and th...Mobile Edge Computing(MEC)is promising to alleviate the computation and storage burdens for terminals in wireless networks.The huge energy consumption of MEC servers challenges the establishment of smart cities and their service time powered by rechargeable batteries.In addition,Orthogonal Multiple Access(OMA)technique cannot utilize limited spectrum resources fully and efficiently.Therefore,Non-Orthogonal Multiple Access(NOMA)-based energy-efficient task scheduling among MEC servers for delay-constraint mobile applications is important,especially in highly-dynamic vehicular edge computing networks.The various movement patterns of vehicles lead to unbalanced offloading requirements and different load pressure for MEC servers.Self-Imitation Learning(SIL)-based Deep Reinforcement Learning(DRL)has emerged as a promising machine learning technique to break through obstacles in various research fields,especially in time-varying networks.In this paper,we first introduce related MEC technologies in vehicular networks.Then,we propose an energy-efficient approach for task scheduling in vehicular edge computing networks based on DRL,with the purpose of both guaranteeing the task latency requirement for multiple users and minimizing total energy consumption of MEC servers.Numerical results demonstrate that the proposed algorithm outperforms other methods.展开更多
Here,the challenges of sample efficiency and navigation performance in deep rein-forcement learning for visual navigation are focused and a deep imitation reinforcement learning approach is proposed.Our contributions ...Here,the challenges of sample efficiency and navigation performance in deep rein-forcement learning for visual navigation are focused and a deep imitation reinforcement learning approach is proposed.Our contributions are mainly three folds:first,a frame-work combining imitation learning with deep reinforcement learning is presented,which enables a robot to learn a stable navigation policy faster in the target-driven navigation task.Second,the surrounding images is taken as the observation instead of sequential images,which can improve the navigation performance for more information.Moreover,a simple yet efficient template matching method is adopted to determine the stop action,making the system more practical.Simulation experiments in the AI-THOR environment show that the proposed approach outperforms previous end-to-end deep reinforcement learning approaches,which demonstrate the effectiveness and efficiency of our approach.展开更多
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
Gesture recognition is topical in computer science and aims at interpreting human gestures via mathematical algorithms. Among the numerous applications are physical rehabilitation and imitation games. In this work, we...Gesture recognition is topical in computer science and aims at interpreting human gestures via mathematical algorithms. Among the numerous applications are physical rehabilitation and imitation games. In this work, we suggest performing human gesture recognition within the context of a serious imitation game, which would aim at improving social interactions with teenagers with autism spectrum disorders. We use an artificial intelligence algorithm to detect the skeleton of the participant, then model the human pose space and describe an imitation learning method using a Gaussian Mixture Model in the Riemannian manifold.展开更多
The imitation cheese is the product with the cheese characteristics which can meet the specific requirements by using the non-milk-derived protein and fat or the full substitution of the milk protein and the milk fat....The imitation cheese is the product with the cheese characteristics which can meet the specific requirements by using the non-milk-derived protein and fat or the full substitution of the milk protein and the milk fat.This paper introduces the production principles,processes and key control points of the imitation cheese with the soybean as main raw material,summarizes the researches and development of the soybean imitation cheese in recent years,and forecasts the market prospect of the soybean imitation cheese in China.展开更多
Imitation models for computing the environmental water pollution level depending on the intensity of pollution sources created by the author over the years are presented. For this purpose, an additive model of a non-s...Imitation models for computing the environmental water pollution level depending on the intensity of pollution sources created by the author over the years are presented. For this purpose, an additive model of a non-stationary random process is considered. For the modeling of its components, models that consider only dilution and self-purification processes are proposed for waste water and three-dimensional turbulent diffusion equations for river waters, and multidimensional Gaussian Markov series are proposed for modeling the random component. The purpose, the capabilities and the peculiarities of such imitation models are discussed taking into account the peculiarities of the water objects. The modular principle of creating imitation models is proposed to facilitate their development and use.展开更多
As an output skill,English writing is regarded as an important means to examine students’integrated language skills.In order to resolve the problems in writing and improve college students’writing competence,this st...As an output skill,English writing is regarded as an important means to examine students’integrated language skills.In order to resolve the problems in writing and improve college students’writing competence,this study tries to explore a new writing teaching method,dictogloss-based imitation writing,in hoping of its effectiveness to writing teaching for the teachers.The effectiveness and feasibility are based on whether it can improve college students’fluency,accuracy and complexity in compositions,and arouse students’interest in writing.展开更多
With a growing number of foreign language studies on proficiency outcomes,it is imperative to address the challenge of measuring students’proficiency development in a language program where standardized proficiency t...With a growing number of foreign language studies on proficiency outcomes,it is imperative to address the challenge of measuring students’proficiency development in a language program where standardized proficiency testing is not readily available.This article reports administering a Chinese elicited imitation test(EIT)by an instructor to track students’global oral proficiency development in a small language program in a mid-size U.S.public university.The test results from the EIT of second language(L2)Chinese suggest that this tool can provide the instructor with valuable insights into students’oral proficiency.This study also discusses the potential practical value of using this EIT in a language program with limited resources for standardized proficiency assessment.The hope is that this study will encourage language educators who are not already doing so to start using empirical evidence from a valid and reliable proficiency measurement tool to reflect on,improve,and guide their instructional practices.展开更多
■Shanghai has always been China'smost receptive city.During the nineteenthcentury,while the rest of the country clungto provincial traditions,Shanghai hadbegun to act as a gateway to the rest ofthe world.Along wi...■Shanghai has always been China'smost receptive city.During the nineteenthcentury,while the rest of the country clungto provincial traditions,Shanghai hadbegun to act as a gateway to the rest ofthe world.Along with the opium展开更多
A schoolboy went home with a pain in his stomach.“Well,sit down and have a drink,”said his mother,“Your stomach’s hurting because it’s empty.It’ll be all right when you’ve got something in it.”
Based on the translated version of“The Root Cause of Poverty”by Rutger Bregman on the Ted speech online platform,this research analyzes the application of direct borrowing,imitative translation and creative translat...Based on the translated version of“The Root Cause of Poverty”by Rutger Bregman on the Ted speech online platform,this research analyzes the application of direct borrowing,imitative translation and creative translation in English-Chinese translation.First,we believe the direct borrowing of a ready-made version is most ideal as it reveals the common ground both languages share when translating a source text.Next,it is preferable to imitate an already existing expression as similarity is reader-friendly.However,it is sometimes necessary to adopt creative translation to preserve differences to ensure that the meaning of the original language is accurately transmitted.展开更多
This paper investigates imitation dynamics with continuously distributed delay.In realistic technological,economic,and social environments,individuals are involved in strategic interactions simultaneously while the in...This paper investigates imitation dynamics with continuously distributed delay.In realistic technological,economic,and social environments,individuals are involved in strategic interactions simultaneously while the influences of their decision-making may not be observable instantaneously.It shows that there exists a time delay effect.Different distributions of delay are further considered to efficiently lucubrate the stability of interior equilibrium in the imitation dynamics with continuous distributions of delay in the two-strategy game contexts.Precisely,when the delay follows the uniform distributions and Gamma distributions,the authors present that interior equilibrium can be asymptotically stable.Furthermore,when the probability density of the delay is general density,the authors also determine a sufficient condition for stability derived from the expected delay.Last but not least,the interested but uncomplicated Snowdrift game is utilized to demonstrate our theoretical results.展开更多
This paper studies imitation learning in nonlinear multi-player game systems with heterogeneous control input dynamics.We propose a model-free data-driven inverse reinforcement learning(RL)algorithm for a leaner to fi...This paper studies imitation learning in nonlinear multi-player game systems with heterogeneous control input dynamics.We propose a model-free data-driven inverse reinforcement learning(RL)algorithm for a leaner to find the cost functions of a N-player Nash expert system given the expert's states and control inputs.This allows us to address the imitation learning problem without prior knowledge of the expert's system dynamics.To achieve this,we provide a basic model-based algorithm that is built upon RL and inverse optimal control.This serves as the foundation for our final model-free inverse RL algorithm which is implemented via neural network-based value function approximators.Theoretical analysis and simulation examples verify the methods.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
Scarlet Bird and Paper Hawk by Ge Liang have inherited the style of novel of society which began with The Plum in the Golden Vase,carefully depicting scenes of daily life and exuding the great charm of antiquity.This ...Scarlet Bird and Paper Hawk by Ge Liang have inherited the style of novel of society which began with The Plum in the Golden Vase,carefully depicting scenes of daily life and exuding the great charm of antiquity.This coincides with the trend in contemporary Chinese literature toward using local resources and seeking cultural identity after the 1990s.However,while the neo-classical texts of Ge Liang are quite realistic in appearance,their inner vitality and spirit cannot be easily replicated.In contrast,the“Jiangnan Trilogy”by Ge Fei is far less imitative of classical novels than the novels of Ge Liang,but the pursuit of utopia is used throughout the trilogy to connect the main storylines of the destinies of four generations of the Lu family and is closely related to China's grand history over the past century.While drawing on ancient Chinese cultural resources,Ge Fei injects brand new and heterogeneous elements into1 hisworks,reviving traditional lyrical styles and creating a new“Chinese poetics.”展开更多
Reinforcement learning(RL)has shown significant success in sequential decision making in fields like autonomous vehicles,robotics,marketing and gaming industries.This success has attracted the attention to the RL cont...Reinforcement learning(RL)has shown significant success in sequential decision making in fields like autonomous vehicles,robotics,marketing and gaming industries.This success has attracted the attention to the RL control approach for building energy systems which are becoming complicated due to the need to optimize for multiple,potentially conflicting,goals like occupant comfort,energy use and grid interactivity.However,for real world applications,RL has several drawbacks like requiring large training data and time,and unstable control behavior during the early exploration process making it infeasible for an application directly to building control tasks.To address these issues,an imitation learning approach is utilized herein where the RL agents starts with a policy transferred from accepted rule based policies and heuristic policies.This approach is successful in reducing the training time,preventing the unstable early exploration behavior and improving upon an accepted rule-based policy-all of these make RL a more practical control approach for real world applications in the domain of building controls.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
文摘The theory of“imitation”in painting occupies a leading position in western art,which originated from the theory of“imitation”in ancient Greece,and has become one of the art theories affecting the world through the continuous development of later generations.Through the exploration of the source of“imitation”in China and the West,there are some comments on the meaning of“imitation”in Chinese classical painting theory,such as“transfer model writing”and“image form”,which is obvious differences from the west.Traditional Chinese painting is a combination of careful observation of natural things and subjective emotions to express their own aesthetic feelings,and ultimately form a vivid artistic conception.Modern imitation is borrowed from Western imitation.In fact,imitation in traditional painting has its own meaning,which contains Chinese aesthetic thought.“Imitation”aesthetics is unique in traditional Chinese painting and is the most important form of painting art.
文摘UG and imitation are two parallel hypotheses trying to answer how childrens language acquisition is realized. Imitation fails to explain how children acquire language; however, it helps a lot in childrens language acquisition.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.71871171,71871173,and 71832010)
文摘One of the assumptions of previous research in evolutionary game dynamics is that individuals use only one rule to update their strategy. In reality, an individual's strategy update rules may change with the environment, and it is possible for an individual to use two or more rules to update their strategy. We consider the case where an individual updates strategies based on the Moran and imitation processes, and establish mixed stochastic evolutionary game dynamics by combining both processes. Our aim is to study how individuals change strategies based on two update rules and how this affects evolutionary game dynamics. We obtain an analytic expression and properties of the fixation probability and fixation times(the unconditional fixation time or conditional average fixation time) associated with our proposed process. We find unexpected results. The fixation probability within the proposed model is independent of the probabilities that the individual adopts the imitation rule update strategy. This implies that the fixation probability within the proposed model is equal to that from the Moran and imitation processes. The one-third rule holds in the proposed mixed model. However, under weak selection, the fixation times are different from those of the Moran and imitation processes because it is connected with the probability that individuals adopt an imitation update rule. Numerical examples are presented to illustrate the relationships between fixation times and the probability that an individual adopts the imitation update rule, as well as between fixation times and selection intensity. From the simulated analysis, we find that the fixation time for a mixed process is greater than that of the Moran process, but is less than that of the imitation process. Moreover, the fixation times for a cooperator in the proposed process increase as the probability of adopting an imitation update increases; however, the relationship becomes more complex than a linear relationship.
基金supported in part by the National Natural Science Foundation of China under Grant 61971084 and Grant 62001073in part by the National Natural Science Foundation of Chongqing under Grant cstc2019jcyj-msxmX0208in part by the open research fund of National Mobile Communications Research Laboratory,Southeast University,under Grant 2020D05.
文摘Mobile Edge Computing(MEC)is promising to alleviate the computation and storage burdens for terminals in wireless networks.The huge energy consumption of MEC servers challenges the establishment of smart cities and their service time powered by rechargeable batteries.In addition,Orthogonal Multiple Access(OMA)technique cannot utilize limited spectrum resources fully and efficiently.Therefore,Non-Orthogonal Multiple Access(NOMA)-based energy-efficient task scheduling among MEC servers for delay-constraint mobile applications is important,especially in highly-dynamic vehicular edge computing networks.The various movement patterns of vehicles lead to unbalanced offloading requirements and different load pressure for MEC servers.Self-Imitation Learning(SIL)-based Deep Reinforcement Learning(DRL)has emerged as a promising machine learning technique to break through obstacles in various research fields,especially in time-varying networks.In this paper,we first introduce related MEC technologies in vehicular networks.Then,we propose an energy-efficient approach for task scheduling in vehicular edge computing networks based on DRL,with the purpose of both guaranteeing the task latency requirement for multiple users and minimizing total energy consumption of MEC servers.Numerical results demonstrate that the proposed algorithm outperforms other methods.
基金National Natural Science Foundation of China,Grant/Award Numbers:61703418,61825305。
文摘Here,the challenges of sample efficiency and navigation performance in deep rein-forcement learning for visual navigation are focused and a deep imitation reinforcement learning approach is proposed.Our contributions are mainly three folds:first,a frame-work combining imitation learning with deep reinforcement learning is presented,which enables a robot to learn a stable navigation policy faster in the target-driven navigation task.Second,the surrounding images is taken as the observation instead of sequential images,which can improve the navigation performance for more information.Moreover,a simple yet efficient template matching method is adopted to determine the stop action,making the system more practical.Simulation experiments in the AI-THOR environment show that the proposed approach outperforms previous end-to-end deep reinforcement learning approaches,which demonstrate the effectiveness and efficiency of our approach.
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.
文摘Gesture recognition is topical in computer science and aims at interpreting human gestures via mathematical algorithms. Among the numerous applications are physical rehabilitation and imitation games. In this work, we suggest performing human gesture recognition within the context of a serious imitation game, which would aim at improving social interactions with teenagers with autism spectrum disorders. We use an artificial intelligence algorithm to detect the skeleton of the participant, then model the human pose space and describe an imitation learning method using a Gaussian Mixture Model in the Riemannian manifold.
文摘The imitation cheese is the product with the cheese characteristics which can meet the specific requirements by using the non-milk-derived protein and fat or the full substitution of the milk protein and the milk fat.This paper introduces the production principles,processes and key control points of the imitation cheese with the soybean as main raw material,summarizes the researches and development of the soybean imitation cheese in recent years,and forecasts the market prospect of the soybean imitation cheese in China.
文摘Imitation models for computing the environmental water pollution level depending on the intensity of pollution sources created by the author over the years are presented. For this purpose, an additive model of a non-stationary random process is considered. For the modeling of its components, models that consider only dilution and self-purification processes are proposed for waste water and three-dimensional turbulent diffusion equations for river waters, and multidimensional Gaussian Markov series are proposed for modeling the random component. The purpose, the capabilities and the peculiarities of such imitation models are discussed taking into account the peculiarities of the water objects. The modular principle of creating imitation models is proposed to facilitate their development and use.
文摘As an output skill,English writing is regarded as an important means to examine students’integrated language skills.In order to resolve the problems in writing and improve college students’writing competence,this study tries to explore a new writing teaching method,dictogloss-based imitation writing,in hoping of its effectiveness to writing teaching for the teachers.The effectiveness and feasibility are based on whether it can improve college students’fluency,accuracy and complexity in compositions,and arouse students’interest in writing.
文摘With a growing number of foreign language studies on proficiency outcomes,it is imperative to address the challenge of measuring students’proficiency development in a language program where standardized proficiency testing is not readily available.This article reports administering a Chinese elicited imitation test(EIT)by an instructor to track students’global oral proficiency development in a small language program in a mid-size U.S.public university.The test results from the EIT of second language(L2)Chinese suggest that this tool can provide the instructor with valuable insights into students’oral proficiency.This study also discusses the potential practical value of using this EIT in a language program with limited resources for standardized proficiency assessment.The hope is that this study will encourage language educators who are not already doing so to start using empirical evidence from a valid and reliable proficiency measurement tool to reflect on,improve,and guide their instructional practices.
文摘■Shanghai has always been China'smost receptive city.During the nineteenthcentury,while the rest of the country clungto provincial traditions,Shanghai hadbegun to act as a gateway to the rest ofthe world.Along with the opium
文摘A schoolboy went home with a pain in his stomach.“Well,sit down and have a drink,”said his mother,“Your stomach’s hurting because it’s empty.It’ll be all right when you’ve got something in it.”
文摘Based on the translated version of“The Root Cause of Poverty”by Rutger Bregman on the Ted speech online platform,this research analyzes the application of direct borrowing,imitative translation and creative translation in English-Chinese translation.First,we believe the direct borrowing of a ready-made version is most ideal as it reveals the common ground both languages share when translating a source text.Next,it is preferable to imitate an already existing expression as similarity is reader-friendly.However,it is sometimes necessary to adopt creative translation to preserve differences to ensure that the meaning of the original language is accurately transmitted.
基金supported by the National Natural Science Foundation of China under Grant No.11271098Guizhou Provincial Science and Technology Fund under Grant No.[2019]1067the Fundamental Funds for Introduction of Talents of Guizhou University under Grant No.[2017]59。
文摘This paper investigates imitation dynamics with continuously distributed delay.In realistic technological,economic,and social environments,individuals are involved in strategic interactions simultaneously while the influences of their decision-making may not be observable instantaneously.It shows that there exists a time delay effect.Different distributions of delay are further considered to efficiently lucubrate the stability of interior equilibrium in the imitation dynamics with continuous distributions of delay in the two-strategy game contexts.Precisely,when the delay follows the uniform distributions and Gamma distributions,the authors present that interior equilibrium can be asymptotically stable.Furthermore,when the probability density of the delay is general density,the authors also determine a sufficient condition for stability derived from the expected delay.Last but not least,the interested but uncomplicated Snowdrift game is utilized to demonstrate our theoretical results.
文摘This paper studies imitation learning in nonlinear multi-player game systems with heterogeneous control input dynamics.We propose a model-free data-driven inverse reinforcement learning(RL)algorithm for a leaner to find the cost functions of a N-player Nash expert system given the expert's states and control inputs.This allows us to address the imitation learning problem without prior knowledge of the expert's system dynamics.To achieve this,we provide a basic model-based algorithm that is built upon RL and inverse optimal control.This serves as the foundation for our final model-free inverse RL algorithm which is implemented via neural network-based value function approximators.Theoretical analysis and simulation examples verify the methods.
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.
文摘Scarlet Bird and Paper Hawk by Ge Liang have inherited the style of novel of society which began with The Plum in the Golden Vase,carefully depicting scenes of daily life and exuding the great charm of antiquity.This coincides with the trend in contemporary Chinese literature toward using local resources and seeking cultural identity after the 1990s.However,while the neo-classical texts of Ge Liang are quite realistic in appearance,their inner vitality and spirit cannot be easily replicated.In contrast,the“Jiangnan Trilogy”by Ge Fei is far less imitative of classical novels than the novels of Ge Liang,but the pursuit of utopia is used throughout the trilogy to connect the main storylines of the destinies of four generations of the Lu family and is closely related to China's grand history over the past century.While drawing on ancient Chinese cultural resources,Ge Fei injects brand new and heterogeneous elements into1 hisworks,reviving traditional lyrical styles and creating a new“Chinese poetics.”
基金This work was authored in part by the National Renewable Energy Laboratory,United States,operated by Alliance for Sustainable Energy,LLC,for the U.S.Department of Energy(DOE)under Contract No.DE-AC36-08GO28308.
文摘Reinforcement learning(RL)has shown significant success in sequential decision making in fields like autonomous vehicles,robotics,marketing and gaming industries.This success has attracted the attention to the RL control approach for building energy systems which are becoming complicated due to the need to optimize for multiple,potentially conflicting,goals like occupant comfort,energy use and grid interactivity.However,for real world applications,RL has several drawbacks like requiring large training data and time,and unstable control behavior during the early exploration process making it infeasible for an application directly to building control tasks.To address these issues,an imitation learning approach is utilized herein where the RL agents starts with a policy transferred from accepted rule based policies and heuristic policies.This approach is successful in reducing the training time,preventing the unstable early exploration behavior and improving upon an accepted rule-based policy-all of these make RL a more practical control approach for real world applications in the domain of building controls.
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.