Search

Policy Distillation (PD) has become an effective method to improve deep reinforcement learning tasks. The core idea of PD is to distill policy knowledge from a teacher agent to a student agent. However, the teacher-student framework requires a well-trained teacher model which is computationally expensive.In the light of online knowledge distillation, we study the knowledge transfer between different policies that can learn diverse knowledge from the same environment.In this work, we propose Online Policy Distillation (OPD) with Decision-Attention (DA), an online learning framework in which different policies operate in the same environment to learn different perspectives of the environment and transfer knowledge to each other to obtain better performance together. With the absence of a well-performance teacher policy, the group-derived targets play a key role in transferring group knowledge to each student policy. However, naive aggregation functions tend to cause student policies quickly homogenize. To address the challenge, we introduce the Decision-Attention module to the online policies distillation framework. The Decision-Attention module can generate a distinct set of weights for each policy to measure the importance of group members. We use the Atari platform for experiments with various reinforcement learning algorithms, including PPO and DQN. In different tasks, our method can perform better than an independent training policy on both PPO and DQN algorithms. This suggests that our OPD-DA can transfer knowledge between different policies well and help agents obtain more rewards.

Multivariate time series forecasting (MTSF) is crucial for decision-making to precisely forecast the future values/trends, based on the complex relationships identified from historical observations of multiple sequences. Recently, Spatial-Temporal Graph Neural Networks (STGNNs) have gradually become the theme of MTSF model as their powerful capability in mining spatial-temporal dependencies, but almost of them heavily rely on the assumption of historical data integrity. In reality, due to factors such as data collector failures and time-consuming repairment, it is extremely challenging to collect the whole historical observations without missing any variable. In this case, STGNNs can only utilize a subset of normal variables and easily suffer from the incorrect spatial-temporal dependency modeling issue, resulting in the degradation of their forecasting performance. To address the problem, in this paper, we propose a novel Graph Interpolation Attention Recursive Network (named GinAR) to precisely model the spatial-temporal dependencies over the limited collected data for forecasting. In GinAR, it consists of two key components, that is, interpolation attention and adaptive graph convolution to take place of the fully connected layer of simple recursive units, and thus are capable of recovering all missing variables and reconstructing the correct spatial-temporal dependencies for recursively modeling of multivariate time series data, respectively. Extensive experiments conducted on five real-world datasets demonstrate that GinAR outperforms 11 SOTA baselines, and even when 90% of variables are missing, it can still accurately predict the future values of all variables., Comment: Accepted by KDD 2024 (Research track)

Multivariate Time Series (MTS) widely exists in real-word complex systems, such as traffic and energy systems, making their forecasting crucial for understanding and influencing these systems. Recently, deep learning-based approaches have gained much popularity for effectively modeling temporal and spatial dependencies in MTS, specifically in Long-term Time Series Forecasting (LTSF) and Spatial-Temporal Forecasting (STF). However, the fair benchmarking issue and the choice of technical approaches have been hotly debated in related work. Such controversies significantly hinder our understanding of progress in this field. Thus, this paper aims to address these controversies to present insights into advancements achieved. To resolve benchmarking issues, we introduce BasicTS, a benchmark designed for fair comparisons in MTS forecasting. BasicTS establishes a unified training pipeline and reasonable evaluation settings, enabling an unbiased evaluation of over 30 popular MTS forecasting models on more than 18 datasets. Furthermore, we highlight the heterogeneity among MTS datasets and classify them based on temporal and spatial characteristics. We further prove that neglecting heterogeneity is the primary reason for generating controversies in technical approaches. Moreover, based on the proposed BasicTS and rich heterogeneous MTS datasets, we conduct an exhaustive and reproducible performance and efficiency comparison of popular models, providing insights for researchers in selecting and designing MTS forecasting models.

Multivariate time series long-term prediction, which aims to predict the change of data in a long time, can provide references for decision-making. Although transformer-based models have made progress in this field, they usually do not make full use of three features of multivariate time series: global information, local information, and variables correlation. To effectively mine the above three features and establish a high-precision prediction model, we propose a double sampling transformer (DSformer), which consists of the double sampling (DS) block and the temporal variable attention (TVA) block. Firstly, the DS block employs down sampling and piecewise sampling to transform the original series into feature vectors that focus on global information and local information respectively. Then, TVA block uses temporal attention and variable attention to mine these feature vectors from different dimensions and extract key information. Finally, based on a parallel structure, DSformer uses multiple TVA blocks to mine and integrate different features obtained from DS blocks respectively. The integrated feature information is passed to the generative decoder based on a multi-layer perceptron to realize multivariate time series long-term prediction. Experimental results on nine real-world datasets show that DSformer can outperform eight existing baselines., Comment: Accepted by CIKM 2023 (FULL paper)