Abstract This paper introduces ShuttleFlow, a simple yet effective model designed to forecast badminton shot types and shuttle positions. This tool could be invaluable for coaches, enabling them to identify opponents’ weaknesses and devise effective strategies accordingly. Given the inherent unpredictability of player behaviors, our model leverages conditional normalizing flow to generate the distributions of shot types and shuttle positions. This is achieved by considering the players and their preceding shots on the court. To augment the performance of our model, especially in predicting outcomes for players who have not previously competed against each other, we incorporate a novel regularization term. Additionally, we utilize Poisson disk sampling to reduce sample redundancy when generating the distributions. Compared to state-of-the-art techniques, our results underscore ShuttleFlow’s effectiveness in forecasting shot types and shuttle positions.

Abstract We introduce NoiseFlow, a generative network that addresses the issue of noisy labels in classification problems by modeling the entire label distribution based on the input data/image. Unlike previous methods, which assign each input to only one specific class, NoiseFlow generates different labels by considering the image and a random noise drawn from a standard normal distribution. This approach improves generalization performance since it does not require extensive parameter adjustments to fit the unknown data noise. To model the label distribution, we use conditional normalizing flows, which are effective at avoiding mode collapse and ensuring the presence of the correct label in the distribution for accurate classification. Moreover, NoiseFlow can be combined with other training strategies, such as mixup interpolation and contrastive learning, to achieve even better performance. We compared NoiseFlow with baseline methods on several synthetic and real-world datasets, and the experiment results demonstrate its effectiveness.

In offline reinforcement learning (RL), updating the value function with the discrete-time Bellman Equation often encounters challenges due to the limited scope of available data. This limitation stems from the Bellman Equation, which cannot accurately predict the value of unvisited states. To address this issue, we have introduced an innovative solution that bridges the continuous- and discrete-time RL methods, capitalizing on their advantages. Our method uses a discrete-time RL algorithm to derive the value function from a dataset while ensuring that the function’s first derivative aligns with the local characteristics of states and actions, as defined by the Hamilton-Jacobi-Bellman equation in continuous RL. We provide practical algorithms for both deterministic policy gradient methods and stochastic policy gradient methods. Experiments on the D4RL dataset show that incorporating the first-order information significantly improves policy performance for offline RL problems.

Domain randomization (DR) is widely used in reinforcement learning (RL) to bridge the gap between simulation and reality by maximizing its average returns under the perturbation of environmental parameters. However, even the most complex simulators cannot capture all details in reality due to finite domain parameters and simplified physical models. Additionally, the existing methods often assume that the distribution of domain parameters belongs to a specific family of probability functions, such as normal distributions, which may not be correct. To overcome these limitations, we propose a new approach to DR by rethinking it from the perspective of adversarial state perturbation, without the need for reconfiguring the simulator or relying on prior knowledge about the environment. We also address the issue of over-conservatism that can occur when perturbing agents to the worst states during training by introducing a Relaxed State-Adversarial Algorithm that simultaneously maximizes the average-case and worst-case returns. We evaluate our method by comparing it to state-of-the-art methods, providing experimental results and theoretical proofs to verify its effectiveness. Our source code and appendix are available at https://github.com/sophialien/RAPPO.

In this study, we used reinforcement learning (RL) models to invest assets in order to earn returns. The models were trained to interact with a simulated environment based on historical market data and learn trading strategies. However, using deep neural networks based on the returns of each period can be challenging due to the unpredictability of financial markets. As a result, the policies learned from training data may not be effective when tested in real-world situations. To address this issue, we incorporated contrastive learning and reward smoothing into our training process. Contrastive learning allows the RL models to recognize patterns in asset states that may indicate future price movements. Reward smoothing, on the other hand, serves as a regularization technique to prevent the models from seeking immediate but uncertain profits. We tested our method against various traditional financial techniques and other deep RL methods, and found it to be effective in both the U.S. stock market and the cryptocurrency market. Our source code is available at https://github.com/sophialien/FinTech-DPM.

We present a colorization network that generates flat-color icons according to given sketches and semantic colorization styles. Our network contains a style-structure disentangled colorization module and a normalizing flow. The colorization module transforms a paired sketch image and style image into a flat-color icon. To enhance network generalization and the quality of icons, we present a pixel-wise decoder, a global style code, and a contour loss to reduce color gradients at flat regions and increase color discontinuity at boundaries. The normalizing flow maps Gaussian vectors to diverse style codes conditioned on the given semantic colorization label. This conditional sampling enables users to control attributes and obtain diverse colorization results. Compared to previous methods built upon conditional generative adversarial networks, our approach enjoys the advantages of both high image quality and diversity. To evaluate its effectiveness, we compared the flat-color icons generated by our approach and recent colorization and image-to-image translation methods on various conditions. Experiment results verify that our method out- performs state-of-the-arts qualitatively and quantitatively.

In this paper, we present a visualization system for users to study multivariate time series data. They first identify trends or anomalies from a global view and then examine details in a local view. Specifically, we train a neural network to project high-dimensional data to a two dimensional (2D) planar space while retaining global data distances. By aligning the 2D points with a predefined color map, high-dimensional data can be represented by colors. Because perceptual color differentiation may fail to reflect data distance, we optimize perceptual color differentiation on each map region by deformation. The region with large perceptual color differentiation will expand, whereas the region with small differentiation will shrink. Since colors do not occupy any space in visualization, we convey the overview of multivariate time series data by a calendar view. Cells in the view are color-coded to represent multivariate data at different time spans. Users can observe color changes over time to identify events of interest. Afterward, they study details of an event by examining parallel coordinate plots. Cells in the calendar view and the parallel coordinate plots are dynamically linked for users to obtain insights that are barely noticeable in large datasets. The experiment results, comparisons, conducted case studies, and the user study indicate that our visualization system is feasible and effective.