Multi-View Reinforcement Learning (MVRL) seeks to provide agents with multi-view observations, enabling them to perceive environment with greater effectiveness and precision. Recent advancements in MVRL focus on extracting latent representations from multiview observations and leveraging them in control tasks. However, it is not straightforward to learn compact and task-relevant representations, particularly in the presence of redundancy, distracting information, or missing views. In this paper, we propose Multi-view Fusion State for Control (MFSC), firstly incorporating bisimulation metric learning into MVRL to learn task-relevant representations. Furthermore, we propose a multiview-based mask and latent reconstruction auxiliary task that exploits shared information across views and improves MFSC’s robustness in missing views by introducing a mask token. Extensive experimental results demonstrate that our method outperforms existing approaches in MVRL tasks. Even in more realistic scenarios with interference or missing views, MFSC consistently maintains high performance. The project code is available at https://github.com/zpwdev/MFSC.

Visual Model-Based Reinforcement Learning (MBRL) promises to encapsulate agent's knowledge about the underlying dynamics of the environment, enabling learning a world model as a useful planner. However, top MBRL agents such as Dreamer often struggle with visual pixel-based inputs in the presence of exogenous or irrelevant noise in the observation space, due to failure to capture task-specific features while filtering out irrelevant spatio-temporal details. To tackle this problem, we apply a spatio-temporal masking strategy, a bisimulation principle, combined with latent reconstruction, to capture endogenous task-specific aspects of the environment for world models, effectively eliminating non-essential information. Joint training of representations, dynamics, and policy often leads to instabilities. To further address this issue, we develop a Hybrid Recurrent State-Space Model (HRSSM) structure, enhancing state representation robustness for effective policy learning. Our empirical evaluation demonstrates significant performance improvements over existing methods in a range of visually complex control tasks such as Maniskill with exogenous distractors from the Matterport environment. Our code is avaliable at https://github.com/bit1029public/HRSSM.

Multivariate time series (MTS) analysis and forecasting are crucial in many real-world applications, such as smart traffic management and weather forecasting. However, most existing work either focuses on short sequence forecasting or makes predictions predominantly with time domain features, which is not effective at removing noises with irregular frequencies in MTS. Therefore, we propose WaveForM, an end-to-end graph enhanced Wavelet learning framework for long sequence FORecasting of MTS. WaveForM first utilizes Discrete Wavelet Transform (DWT) to represent MTS in the wavelet domain, which captures both frequency and time domain features with a sound theoretical basis. To enable the effective learning in the wavelet domain, we further propose a graph constructor, which learns a global graph to represent the relationships between MTS variables, and graph-enhanced prediction modules, which utilize dilated convolution and graph convolution to capture the correlations between time series and predict the wavelet coefficients at different levels. Extensive experiments on five real-world forecasting datasets show that our model can achieve considerable performance improvement over different prediction lengths against the most competitive baseline of each dataset.

Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs can contain irrelevant and exogenous information. In this work, we study how information bottlenecjs can be used to construct latent states efficiently in the presence of task irrelevant information. We propose architectures that utilize variational and discrete information bottleneck, coined as RepDIB, to learn structured factorized representations. Exploiting the expressiveness bought by factorized representations, we introduce a simple, yet effective, bottleneck that can be integrated with any existing self supervised objective for RL. We demonstrate this across several online and offline RL benchmarks, along with a real robot arm task, where we find that compressed representations with RepDIB can lead to strong performance improvements, as the learnt bottlenecks can help predict only the relevant state, while ignoring irrelevant information.

Learning to control an agent from offline data collected in a rich pixel-based visual observation space is vital for real-world applications of reinforcement learning (RL). A major challenge in this setting is the presence of input information that is hard to model and irrelevant to controlling the agent. This problem has been approached by the theoretical RL community through the lens of *exogenous information*, i.e., any control-irrelevant information contained in observations. For example, a robot navigating in busy streets needs to ignore irrelevant information, such as other people walking in the background, textures of objects, or birds in the sky. In this paper, we focus on the setting with visually detailed exogenous information and introduce new offline RL benchmarks that offer the ability to study this problem. We find that contemporary representation learning techniques can fail on datasets where the noise is a complex and time-dependent process, which is prevalent in practical applications. To address these, we propose to use multi-step inverse models to learn Agent-Centric Representations for Offline-RL (ACRO). Despite being simple and reward-free, we show theoretically and empirically that the representation created by this objective greatly outperforms baselines.

While bisimulation-based approaches hold promise for learning robust state representations for Reinforcement Learning (RL) tasks, their efficacy in offline RL tasks has not been up to par. In some instances, their performance has even significantly underperformed alternative methods. We aim to understand why bisimulation methods succeed in online settings, but falter in offline tasks. Our analysis reveals that missing transitions in the dataset are particularly harmful to the bisimulation principle, leading to ineffective estimation. We also shed light on the critical role of reward scaling in bounding the scale of bisimulation measurements and of the value error they induce. Based on these findings, we propose to apply the expectile operator for representation learning to our offline RL setting, which helps to prevent overfitting to incomplete data. Meanwhile, by introducing an appropriate reward scaling strategy, we avoid the risk of feature collapse in representation space. We implement these recommendations on two state-of-the-art bisimulation-based algorithms, MICo and SimSR, and demonstrate performance gains on two benchmark suites: D4RL and Visual D4RL. Codes are provided at \url{https://github.com/zanghyu/Offline_Bisimulation}.

This work explores how to learn robust and generalizable state representation from image-based observations with deep reinforcement learning methods. Addressing the computational complexity, stringent assumptions and representation collapse challenges in existing work of bisimulation metric, we devise Simple State Representation (SimSR) operator. SimSR enables us to design a stochastic approximation method that can practically learn the mapping functions (encoders) from observations to latent representation space. In addition to the theoretical analysis and comparison with the existing work, we experimented and compared our work with recent state-of-the-art solutions in visual MuJoCo tasks. The results shows that our model generally achieves better performance and has better robustness and good generalization.

Goal-conditioned reinforcement learning (RL) is a promising direction for training agents that are capable of solving multiple tasks and reach a diverse set of objectives. How to \textit{specify} and \textit{ground} these goals in such a way that we can both reliably reach goals during training as well as generalize to new goals during evaluation remains an open area of research. Defining goals in the space of noisy, high-dimensional sensory inputs is one possibility, yet this poses a challenge for training goal-conditioned agents, or even for generalization to novel goals. We propose to address this by learning compositional representations of goals and processing the resulting representation via a discretization bottleneck, for coarser specification of goals, through an approach we call DGRL. We show that discretizing outputs from goal encoders through a bottleneck can work well in goal-conditioned RL setups, by experimentally evaluating this method on tasks ranging from maze environments to complex robotic navigation and manipulation tasks. Additionally, we show a theoretical result which bounds the expected return for goals not observed during training, while still allowing for specifying goals with expressive combinatorial structure.

Next Point-of-interest (POI) recommendation is a key task in improving location-related customer experiences and business operations, but yet remains challenging due to the substantial diversity of human activities and the sparsity of the check-in records available. To address these challenges, we proposed to explore the category hierarchy knowledge graph of POIs via an attention mechanism to learn the robust representations of POIs even when there is insufficient data. We also proposed a spatial-temporal decay LSTM and a Discrete Fourier Series-based periodic attention to better facilitate the capturing of the personalized behavior pattern. Extensive experiments on two commonly adopted real-world location-based social networks (LBSNs) datasets proved that the inclusion of the aforementioned modules helps to boost the performance of next and next new POI recommendation tasks significantly. Specifically, our model in general outperforms other state-of-the-art methods by a large margin.

Punning is a creative way to make conversation enjoyable and literary writing elegant.In this paper, we focus on the task of generating a pun sentence given a pair of homophones.We first find the constraint words supporting the semantic incongruity for a sentence.Then we rewrite the sentence with explicit positive and negative constraints.Our model achieves the state-of-the-art results in both automatic and human evaluations.We further make an error analysis and discuss the challenges for the computational pun models.

One of the most challenging part of recipe generation is to deal with the complex restrictions among the input ingredients.Previous researches simplify the problem by treating the inputs independently and generating recipes containing as much information as possible.In this work, we propose a routing method to dive into the content selection under the internal restrictions.The routing enforced generative model (RGM) can generate appropriate recipes according to the given ingredients and user preferences.Our model yields new stateof-the-art results on the recipe generation task with significant improvements on BLEU, F1 and human evaluation.

In this paper, we explore a new approach for automated chess commentary generation, which aims to generate chess commentary texts in different categories (e.g., description, comparison, planning, etc.).We introduce a neural chess engine into text generation models to help with encoding boards, predicting moves, and analyzing situations.By jointly training the neural chess engine and the generation models for different categories, the models become more effective.We conduct experiments on 5 categories in a benchmark Chess Commentary dataset and achieve inspiring results in both automatic and human evaluations.

Alignment of multiple multi-relational networks, such as knowledge graphs, is vital for AI applications. Different from the conventional alignment models, we apply the graph convolutional network (GCN) to achieve more robust network embedding for the alignment task. In comparison with existing GCNs which cannot fully utilize multi-relation information, we propose a vectorized relational graph convolutional network (VR-GCN) to learn the embeddings of both graph entities and relations simultaneously for multi-relational networks. The role discrimination and translation property of knowledge graphs are adopted in the convolutional process. Thereafter, AVR-GCN, the alignment framework based on VR-GCN, is developed for multi-relational network alignment tasks. Anchors are used to supervise the objective function which aims at minimizing the distances between anchors, and to generate new cross-network triplets to build a bridge between different knowledge graphs at the level of triplet to improve the performance of alignment. Experiments on real-world datasets show that the proposed solutions outperform the state-of-the-art methods in terms of network embedding, entity alignment, and relation alignment.

Data-to-text generation is very essential and important in machine writing applications.The recent deep learning models, like Recurrent Neural Networks (RNNs), have shown a bright future for relevant text generation tasks.However, rare work has been done for automatic generation of long reviews from user opinions.In this paper, we introduce a deep neural network model to generate long Chinese reviews from aspect-sentiment scores representing users' opinions.We conduct our study within the framework of encoderdecoder networks, and we propose a hierarchical structure with aligned attention in the Long-Short Term Memory (LSTM) decoder.Experiments show that our model outperforms retrieval based baseline methods, and also beats the sequential generation models in qualitative evaluations.