亚洲男人的天堂2018av,欧美草比,久久久久久免费视频精选,国色天香在线看免费,久久久久亚洲av成人片仓井空

Offline reinforcement learning (RL) concerns pursuing an optimal policy for sequential decision-making from a pre-collected dataset, without further interaction with the environment. Recent theoretical progress has focused on developing sample-efficient offline RL algorithms with various relaxed assumptions on data coverage and function approximators, especially to handle the case with excessively large state-action spaces. Among them, the framework based on the linear-programming (LP) reformulation of Markov decision processes has shown promise: it enables sample-efficient offline RL with function approximation, under only partial data coverage and realizability assumptions on the function classes, with favorable computational tractability. In this work, we revisit the LP framework for offline RL, and advance the existing results in several aspects, relaxing certain assumptions and achieving optimal statistical rates in terms of sample size. Our key enabler is to introduce proper constraints in the reformulation, instead of using any regularization as in the literature, sometimes also with careful choices of the function classes and initial state distributions. We hope our insights further advocate the study of the LP framework, as well as the induced primal-dual minimax optimization, in offline RL.

We aim at estimating in a non-parametric way the density $\pi$ of the stationary distribution of a $d$-dimensional stochastic differential equation $(X_t)_{t \in [0, T]}$, for $d \ge 2$, from the discrete observations of a finite sample $X_{t_0}$, ... , $X_{t_n}$ with $0= t_0 < t_1 < ... < t_n =: T_n$. We propose a kernel density estimator and we study its convergence rates for the pointwise estimation of the invariant density under anisotropic H\"older smoothness constraints. First of all, we find some conditions on the discretization step that ensures it is possible to recover the same rates as if the continuous trajectory of the process was available. Such rates are optimal and new in the context of density estimator. Then we deal with the case where such a condition on the discretization step is not satisfied, which we refer to as intermediate regime. In this new regime we identify the convergence rate for the estimation of the invariant density over anisotropic H\"older classes, which is the same convergence rate as for the estimation of a probability density belonging to an anisotropic H\"older class, associated to $n$ iid random variables $X_1, ..., X_n$. After that we focus on the asynchronous case, in which each component can be observed at different time points. Even if the asynchronicity of the observations complexifies the computation of the variance of the estimator, we are able to find conditions ensuring that this variance is comparable to the one of the continuous case. We also exhibit that the non synchronicity of the data introduces additional bias terms in the study of the estimator.

We present a change-blindness based redirected walking algorithm that allows a user to explore on foot a virtual indoor environment consisting of an infinite number of rooms while at the same time ensuring collision-free walking for the user in real space. This method uses change blindness to scale and translate the room without the user's awareness by moving the wall while the user is not looking. Consequently, the virtual room containing the current user always exists in the valid real space. We measured the detection threshold for whether the user recognizes the movement of the wall outside the field of view. Then, we used the measured detection threshold to determine the amount of changing the dimension of the room by moving that wall. We conducted a live-user experiment to navigate the same virtual environment using the proposed method and other existing methods. As a result, users reported higher usability, presence, and immersion when using the proposed method while showing reduced motion sickness compared to other methods. Hence, our approach can be used to implement applications to allow users to explore an infinitely large virtual indoor environment such as virtual museum and virtual model house while simultaneously walking in a small real space, giving users a more realistic experience.

Applying changes to an input speech signal to change the perceived speaker of speech to a target while maintaining the content of the input is a challenging but interesting task known as Voice conversion (VC). Over the last few years, this task has gained significant interest where most systems use data-driven machine learning models. Doing the conversion in a low-latency real-world scenario is even more challenging constrained by the availability of high-quality data. Data augmentations such as pitch shifting and noise addition are often used to increase the amount of data used for training machine learning based models for this task. In this paper we explore the efficacy of common data augmentation techniques for real-time voice conversion and introduce novel techniques for data augmentation based on audio and voice transformation effects as well. We evaluate the conversions for both male and female target speakers using objective and subjective evaluation methodologies.

Efficient exploration strategy is one of essential issues in cooperative multi-agent reinforcement learning (MARL) algorithms requiring complex coordination. In this study, we introduce a new exploration method with the strangeness that can be easily incorporated into any centralized training and decentralized execution (CTDE)-based MARL algorithms. The strangeness refers to the degree of unfamiliarity of the observations that an agent visits. In order to give the observation strangeness a global perspective, it is also augmented with the the degree of unfamiliarity of the visited entire state. The exploration bonus is obtained from the strangeness and the proposed exploration method is not much affected by stochastic transitions commonly observed in MARL tasks. To prevent a high exploration bonus from making the MARL training insensitive to extrinsic rewards, we also propose a separate action-value function trained by both extrinsic reward and exploration bonus, on which a behavioral policy to generate transitions is designed based. It makes the CTDE-based MARL algorithms more stable when they are used with an exploration method. Through a comparative evaluation in didactic examples and the StarCraft Multi-Agent Challenge, we show that the proposed exploration method achieves significant performance improvement in the CTDE-based MARL algorithms.

Interactive data exploration (IDE) is an effective way of comprehending big data, whose volume and complexity are beyond human abilities. The main goal of IDE is to discover user interest regions from a database through multi-rounds of user labelling. Existing IDEs adopt active-learning framework, where users iteratively discriminate or label the interestingness of selected tuples. The process of data exploration can be viewed as the process of training a classifier, which determines whether a database tuple is interesting to a user. An efficient exploration thus takes very few iterations of user labelling to reach the data region of interest. In this work, we consider the data exploration as the process of few-shot learning, where the classifier is learned with only a few training examples, or exploration iterations. To this end, we propose a learning-to-explore framework, based on meta-learning, which learns how to learn a classifier with automatically generated meta-tasks, so that the exploration process can be much shortened. Extensive experiments on real datasets show that our proposal outperforms existing explore-by-example solutions in terms of accuracy and efficiency.

This paper proposes a novel approach for learning a data-driven quadratic manifold from high-dimensional data, then employing this quadratic manifold to derive efficient physics-based reduced-order models. The key ingredient of the approach is a polynomial mapping between high-dimensional states and a low-dimensional embedding. This mapping consists of two parts: a representation in a linear subspace (computed in this work using the proper orthogonal decomposition) and a quadratic component. The approach can be viewed as a form of data-driven closure modeling, since the quadratic component introduces directions into the approximation that lie in the orthogonal complement of the linear subspace, but without introducing any additional degrees of freedom to the low-dimensional representation. Combining the quadratic manifold approximation with the operator inference method for projection-based model reduction leads to a scalable non-intrusive approach for learning reduced-order models of dynamical systems. Applying the new approach to transport-dominated systems of partial differential equations illustrates the gains in efficiency that can be achieved over approximation in a linear subspace.

Riemannian Gaussian distributions were initially introduced as basic building blocks for learning models which aim to capture the intrinsic structure of statistical populations of positive-definite matrices (here called covariance matrices). While the potential applications of such models have attracted significant attention, a major obstacle still stands in the way of these applications: there seems to exist no practical method of computing the normalising factors associated with Riemannian Gaussian distributions on spaces of high-dimensional covariance matrices. The present paper shows that this missing method comes from an unexpected new connection with random matrix theory. Its main contribution is to prove that Riemannian Gaussian distributions of real, complex, or quaternion covariance matrices are equivalent to orthogonal, unitary, or symplectic log-normal matrix ensembles. This equivalence yields a highly efficient approximation of the normalising factors, in terms of a rather simple analytic expression. The error due to this approximation decreases like the inverse square of dimension. Numerical experiments are conducted which demonstrate how this new approximation can unlock the difficulties which have impeded applications to real-world datasets of high-dimensional covariance matrices. The paper then turns to Riemannian Gaussian distributions of block-Toeplitz covariance matrices. These are equivalent to yet another kind of random matrix ensembles, here called "acosh-normal" ensembles. Orthogonal and unitary "acosh-normal" ensembles correspond to the cases of block-Toeplitz with Toeplitz blocks, and block-Toeplitz (with general blocks) covariance matrices, respectively.

Bid optimization for online advertising from single advertiser's perspective has been thoroughly investigated in both academic research and industrial practice. However, existing work typically assume competitors do not change their bids, i.e., the wining price is fixed, leading to poor performance of the derived solution. Although a few studies use multi-agent reinforcement learning to set up a cooperative game, they still suffer the following drawbacks: (1) They fail to avoid collusion solutions where all the advertisers involved in an auction collude to bid an extremely low price on purpose. (2) Previous works cannot well handle the underlying complex bidding environment, leading to poor model convergence. This problem could be amplified when handling multiple objectives of advertisers which are practical demands but not considered by previous work. In this paper, we propose a novel multi-objective cooperative bid optimization formulation called Multi-Agent Cooperative bidding Games (MACG). MACG sets up a carefully designed multi-objective optimization framework where different objectives of advertisers are incorporated. A global objective to maximize the overall profit of all advertisements is added in order to encourage better cooperation and also to protect self-bidding advertisers. To avoid collusion, we also introduce an extra platform revenue constraint. We analyze the optimal functional form of the bidding formula theoretically and design a policy network accordingly to generate auction-level bids. Then we design an efficient multi-agent evolutionary strategy for model optimization. Offline experiments and online A/B tests conducted on the Taobao platform indicate both single advertiser's objective and global profit have been significantly improved compared to state-of-art methods.

It is a common paradigm in object detection frameworks to treat all samples equally and target at maximizing the performance on average. In this work, we revisit this paradigm through a careful study on how different samples contribute to the overall performance measured in terms of mAP. Our study suggests that the samples in each mini-batch are neither independent nor equally important, and therefore a better classifier on average does not necessarily mean higher mAP. Motivated by this study, we propose the notion of Prime Samples, those that play a key role in driving the detection performance. We further develop a simple yet effective sampling and learning strategy called PrIme Sample Attention (PISA) that directs the focus of the training process towards such samples. Our experiments demonstrate that it is often more effective to focus on prime samples than hard samples when training a detector. Particularly, On the MSCOCO dataset, PISA outperforms the random sampling baseline and hard mining schemes, e.g. OHEM and Focal Loss, consistently by more than 1% on both single-stage and two-stage detectors, with a strong backbone ResNeXt-101.