Agent actions planning is a challenging problem in multi-agent reinforcement learning. Recent methods typically build their predictive models by full connection layers, but the shortage of utilizing action and observa...
详细信息
In this paper, the $\mathcal{L}_{1}$ -gain based filtering problem for nonlinear positive semi-Markov jump systems is investigated by proposing a novel asynchronous design approach. More precisely, the mode-dependent...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
In this paper, the $\mathcal{L}_{1}$ -gain based filtering problem for nonlinear positive semi-Markov jump systems is investigated by proposing a novel asynchronous design approach. More precisely, the mode-dependent filters are designed in terms of practical observed modes instead of true system modes, such that less conservatism can be achieved. In addition, the effect of time-varying delays is taken into account for more robustness and applicability. By selecting suitable stochastic Lyapunov-Krasovskii functions and applying the linear programming method, sufficient conditions are established to fulfill the desired $\mathcal{L}_{1}$ -gain performance. Eventually, the illustrative simulation is performed to verify the effectiveness of our developed control scheme.
This work presents a memetic Shuffled Frog Leaping Algorithm(SFLA)based tuning approach of an Integral Sliding Mode controller(ISMC)for a quadrotor type of Unmanned Aerial Vehicles(UAV).Based on the Newton–Euler form...
详细信息
This work presents a memetic Shuffled Frog Leaping Algorithm(SFLA)based tuning approach of an Integral Sliding Mode controller(ISMC)for a quadrotor type of Unmanned Aerial Vehicles(UAV).Based on the Newton–Euler formalism,a nonlinear dynamic model of the studied quadrotor is firstly established for control design *** the main parameters of the ISMC design are the gains of the sliding surfaces and signum functions of the switching control law,which are usually selected by repetitive and time-consuming trials-errors based procedures,a constrained optimization problem is formulated for the systematically tuning of these unknown *** time-domain operating constraints,such an optimization-based tuning problem is effectively solved using the proposed SFLA metaheuristic with an empirical comparison to other evolutionary computation-and swarm intelligence-based algorithms such as the Crow Search Algorithm(CSA),Fractional Particle Swarm Optimization Memetic Algorithm(FPSOMA),Ant Bee Colony(ABC)and Harmony Search Algorithm(HSA).Numerical experiments are carried out for various sets of algorithms’parameters to achieve optimal gains of the sliding mode controllers for the altitude and attitude dynamics *** studies revealed that the SFLA is a competitive and easily implemented algorithm with high performance in terms of robustness and non-premature *** results verified that the proposed metaheuristicsbased approach is a promising alternative for the systematic tuning of the effective design parameters in the integral sliding mode control framework.
The symmetry-based decompositions of finite games are investigated. First, the vector space of finite games is decomposed into a symmetric subspace and an orthogonal complement of the symmetric subspace. The bases of ...
详细信息
The symmetry-based decompositions of finite games are investigated. First, the vector space of finite games is decomposed into a symmetric subspace and an orthogonal complement of the symmetric subspace. The bases of the symmetric subspace and those of its orthogonal complement are ***, the potential-based orthogonal decompositions of two-player symmetric/antisymmetric games are presented. The bases and dimensions of all dual decomposed subspaces are revealed. Finally, some properties of these decomposed subspaces are obtained.
We consider the problem of traffic density reconstruction using measurements from probe vehicles (PVs) with a low penetration rate. In other words, the number of sensors is small compared to the number of vehicles on ...
详细信息
ISBN:
(纸本)9781665436601
We consider the problem of traffic density reconstruction using measurements from probe vehicles (PVs) with a low penetration rate. In other words, the number of sensors is small compared to the number of vehicles on the road. The model used assumes noisy measurements and a partially unknown first-order model. All these considerations make the use of machine learning to reconstruct the state the only applicable solution. We first investigate how the identification and reconstruction processes can be merged and how a sparse dataset can still enable a good identification. Secondly, we propose a pre-training procedure that aids the hyperparameter tuning, preventing the gradient descent algorithm from getting stuck at saddle points. Examples using numerical simulations and the SUMO traffic simulator show that the reconstructions are close to the real density in all cases.
At present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train ...
详细信息
This paper investigates poisoning attacks against data-driven control methods. This work is motivated by recent trends showing that, in supervised learning, slightly modifying the data in a malicious manner can drasti...
详细信息
Central Asia is one of the largest arid areas on earth,yet little is known about the concentration levels and risks of mercury(Hg)in the soils of this *** this study,extensive sampling of topsoils(0-10 cm)from represe...
详细信息
Central Asia is one of the largest arid areas on earth,yet little is known about the concentration levels and risks of mercury(Hg)in the soils of this *** this study,extensive sampling of topsoils(0-10 cm)from representative landscapes was carried out over Central Asia(i.e.,Tajikistan,Uzbekistan,and Kyrgyzstan).The total mercury(THg)concentrations in topsoils varied widely from 1.6 to 908.0 ng/g,with high values observed in samples collected in the capital cities and urban *** THg concentrations among different landscapes showed a decreasing order of urban(79.8±184.0 ng/g)>woodland(27.3±28.9 ng/g)>grassland(20.6±15.9 ng/g)>farmland(18.3±9.5 ng/g)>desert(12.3±8.0 ng/g).High THg concentrations were found in the capital cities/urban clusters,followed by a gradual decrease towards the *** concentrations were found to be negatively correlated with the distance from the sampling sites to their nearest cities,indicating that anthropogenic emissions significantly influenced the spatial distribution of topsoil Hg.A significant correlation between THg concentrations and topsoil total organic carbon(TOC)contents was also observed,suggesting that TOC played an essential role in the spatial distribution of topsoil *** assessments of pollution and potential ecological risk suggested that topsoils in highly densely-populated areas were contaminated by Hg and had higher degrees of potential ecological *** health risk assessment results showed that the exposure risk of topsoil Hg to children was higher than that to ***,there was no unacceptable human health risk of topsoil *** study clarified the spatial distribution and risks of Hg in the Central Asian topsoils,offering new insight into the risk prevention and control of soil Hg.
We develop a fast smoothing procedure for solving linear two-stage stochastic programs, which outperforms the well-known L-shaped algorithm on large-scale benchmarks. We derive problem-dependent bounds for the effect ...
详细信息
ISBN:
(纸本)9781665436601
We develop a fast smoothing procedure for solving linear two-stage stochastic programs, which outperforms the well-known L-shaped algorithm on large-scale benchmarks. We derive problem-dependent bounds for the effect of smoothing and characterize the convergence rate of the proposed algorithm. The theory suggests that the smoothing scheme can be sped up by sacrificing accuracy in the final solution. To obtain an efficient and effective method, we suggest a hybrid solution that combines the speed of the smoothing scheme with the accuracy of the L-shaped algorithm. We benchmark a parallel implementation of the smoothing scheme against an efficient parallelized L-shaped algorithm on three large-scale stochastic programs, in a distributed environment with 32 worker cores. The smoothing scheme reduces the solution time by up to an order of magnitude compared to L-shaped.
This work investigates the problem of analyzing privacy of abrupt changes for general Markov processes. These processes may be affected by changes, or exogenous signals, that need to remain private. Privacy refers to ...
详细信息
ISBN:
(纸本)9781665436601
This work investigates the problem of analyzing privacy of abrupt changes for general Markov processes. These processes may be affected by changes, or exogenous signals, that need to remain private. Privacy refers to the disclosure of information of these changes through observations of the underlying Markov chain. In contrast to previous work on privacy, we study the problem for an online sequence of data. We use theoretical tools from optimal detection theory to motivate a definition of online privacy based on the average amount of information per observation of the stochastic system in consideration. Two cases are considered: the full-information case, where the eavesdropper measures all but the signals that indicate a change, and the limited-information case, where the eavesdropper only measures the state of the Markov process. For both cases, we provide ways to derive privacy upper-bounds and compute policies that attain a higher privacy level. It turns out that the problem of computing privacy-aware policies is concave, and we conclude with some examples and numerical simulations for both cases.
暂无评论