Dealing with missing data poses significant challenges in predictive analysis, often leading to biased conclusions when oversimplified assumptions about the missing data process are made. In cases where the data are missing not at random (MNAR), jointly modeling the data and missing data indicators is essential. Motivated by a real data application with partially missing multivariate outcomes related to leaf photosynthetic traits and several environmental covariates, we propose two methods under a selection model framework for handling data with missingness in the response variables suitable for recovering various missingness mechanisms. Both approaches use a multivariate extension of Bayesian additive regression trees (BART) to flexibly model the outcomes. The first approach simultaneously uses a probit regression model to jointly model the missingness. In scenarios where the relationship between the missingness and the data is more complex or non-linear, we propose a second approach using a probit BART model to characterize the missing data process, thereby employing two BART models simultaneously. Both models also effectively handle ignorable covariate missingness. The efficacy of both models compared to existing missing data approaches is demonstrated through extensive simulations, in both univariate and multivariate settings, and through the aforementioned application to the leaf photosynthetic trait data.

Dynamic graphs exhibit intertwined spatio-temporal evolutionary patterns, widely existing in the real world. Nevertheless, the structure incompleteness, noise, and redundancy result in poor robustness for Dynamic Graph Neural Networks (DGNNs). Dynamic Graph Structure Learning (DGSL) offers a promising way to optimize graph structures. However, aside from encountering unacceptable quadratic complexity, it overly relies on heuristic priors, making it hard to discover underlying predictive patterns. How to efficiently refine the dynamic structures, capture intrinsic dependencies, and learn robust representations, remains under-explored. In this work, we propose the novel DG-Mamba, a robust and efficient Dynamic Graph structure learning framework with the Selective State Space Models (Mamba). To accelerate the spatio-temporal structure learning, we propose a kernelized dynamic message-passing operator that reduces the quadratic time complexity to linear. To capture global intrinsic dynamics, we establish the dynamic graph as a self-contained system with State Space Model. By discretizing the system states with the cross-snapshot graph adjacency, we enable the long-distance dependencies capturing with the selective snapshot scan. To endow learned dynamic structures more expressive with informativeness, we propose the self-supervised Principle of Relevant Information for DGSL to regularize the most relevant yet least redundant information, enhancing global robustness. Extensive experiments demonstrate the superiority of the robustness and efficiency of our DG-Mamba compared with the state-of-the-art baselines against adversarial attacks.

Many of the world's most pressing issues, such as climate change and global peace, require complex collective problem-solving skills. Recent studies indicate that diversity in individuals' behaviors is key to developing such skills and increasing collective performance. Yet behavioral diversity in collective artificial learning is understudied, with today's machine learning paradigms commonly favoring homogeneous agent strategies over heterogeneous ones, mainly due to computational considerations. In this work, we employ novel diversity measurement and control paradigms to study the impact of behavioral heterogeneity in several facets of collective artificial learning. Through experiments in team play and other cooperative tasks, we show the emergence of unbiased behavioral roles that improve team outcomes; how neural diversity synergizes with morphological diversity; how diverse agents are more effective at finding cooperative solutions in sparse reward settings; and how behaviorally heterogeneous teams learn and retain latent skills to overcome repeated disruptions. Overall, our results indicate that, by controlling diversity, we can obtain non-trivial benefits over homogeneous training paradigms, demonstrating that diversity is a fundamental component of collective artificial learning, an insight thus far overlooked.

In recent years, reinforcement learning (RL)-based methods for learning driving policies have gained increasing attention in the autonomous driving community and have achieved remarkable progress in various driving scenarios. However, traditional RL approaches rely on manually engineered rewards, which require extensive human effort and often lack generalizability. To address these limitations, we propose \textbf{VLM-RL}, a unified framework that integrates pre-trained Vision-Language Models (VLMs) with RL to generate reward signals using image observation and natural language goals. The core of VLM-RL is the contrasting language goal (CLG)-as-reward paradigm, which uses positive and negative language goals to generate semantic rewards. We further introduce a hierarchical reward synthesis approach that combines CLG-based semantic rewards with vehicle state information, improving reward stability and offering a more comprehensive reward signal. Additionally, a batch-processing technique is employed to optimize computational efficiency during training. Extensive experiments in the CARLA simulator demonstrate that VLM-RL outperforms state-of-the-art baselines, achieving a 10.5\% reduction in collision rate, a 104.6\% increase in route completion rate, and robust generalization to unseen driving scenarios. Furthermore, VLM-RL can seamlessly integrate almost any standard RL algorithms, potentially revolutionizing the existing RL paradigm that relies on manual reward engineering and enabling continuous performance improvements. The demo video and code can be accessed at: https://zilin-huang.github.io/VLM-RL-website.

Recently, deep Multi-Agent Reinforcement Learning (MARL) has demonstrated its potential to tackle complex cooperative tasks, pushing the boundaries of AI in collaborative environments. However, the efficiency of these systems is often compromised by inadequate sample utilization and a lack of diversity in learning strategies. To enhance MARL performance, we introduce a novel sample reuse approach that dynamically adjusts policy updates based on observation novelty. Specifically, we employ a Random Network Distillation (RND) network to gauge the novelty of each agent's current state, assigning additional sample update opportunities based on the uniqueness of the data. We name our method Multi-Agent Novelty-GuidEd sample Reuse (MANGER). This method increases sample efficiency and promotes exploration and diverse agent behaviors. Our evaluations confirm substantial improvements in MARL effectiveness in complex cooperative scenarios such as Google Research Football and super-hard StarCraft II micromanagement tasks.

Reinforcement learning (RL) can be formulated as a sequence modeling problem, where models predict future actions based on historical state-action-reward sequences. Current approaches typically require long trajectory sequences to model the environment in offline RL settings. However, these models tend to over-rely on memorizing long-term representations, which impairs their ability to effectively attribute importance to trajectories and learned representations based on task-specific relevance. In this work, we introduce AdaCred, a novel approach that represents trajectories as causal graphs built from short-term action-reward-state sequences. Our model adaptively learns control policy by crediting and pruning low-importance representations, retaining only those most relevant for the downstream task. Our experiments demonstrate that AdaCred-based policies require shorter trajectory sequences and consistently outperform conventional methods in both offline reinforcement learning and imitation learning environments.

The analysis of dynamical systems is a fundamental tool in the natural sciences and engineering. It is used to understand the evolution of systems as large as entire galaxies and as small as individual molecules. With predefined conditions on the evolution of dy-namical systems, the underlying differential equations have to fulfill specific constraints in time and space. This class of problems is known as boundary value problems. This thesis presents novel approaches to learn time-reversible deterministic and stochastic dynamics constrained by initial and final conditions. The dynamics are inferred by machine learning algorithms from observed data, which is in contrast to the traditional approach of solving differential equations by numerical integration. The work in this thesis examines a set of problems of increasing difficulty each of which is concerned with learning a different aspect of the dynamics. Initially, we consider learning deterministic dynamics from ground truth solutions which are constrained by deterministic boundary conditions. Secondly, we study a boundary value problem in discrete state spaces, where the forward dynamics follow a stochastic jump process and the boundary conditions are discrete probability distributions. In particular, the stochastic dynamics of a specific jump process, the Ehrenfest process, is considered and the reverse time dynamics are inferred with machine learning. Finally, we investigate the problem of inferring the dynamics of a continuous-time stochastic process between two probability distributions without any reference information. Here, we propose a novel criterion to learn time-reversible dynamics of two stochastic processes to solve the Schr\"odinger Bridge Problem.

Transfer learning aims to transfer knowledge or information from a source domain to a relevant target domain. In this paper, we understand transfer learning from the perspectives of knowledge transferability and trustworthiness. This involves two research questions: How is knowledge transferability quantitatively measured and enhanced across domains? Can we trust the transferred knowledge in the transfer learning process? To answer these questions, this paper provides a comprehensive review of trustworthy transfer learning from various aspects, including problem definitions, theoretical analysis, empirical algorithms, and real-world applications. Specifically, we summarize recent theories and algorithms for understanding knowledge transferability under (within-domain) IID and non-IID assumptions. In addition to knowledge transferability, we review the impact of trustworthiness on transfer learning, e.g., whether the transferred knowledge is adversarially robust or algorithmically fair, how to transfer the knowledge under privacy-preserving constraints, etc. Beyond discussing the current advancements, we highlight the open questions and future directions for understanding transfer learning in a reliable and trustworthy manner.

This paper investigates the use of multi-agent reinforcement learning (MARL) to address distributed channel access in wireless local area networks. In particular, we consider the challenging yet more practical case where the agents heterogeneously adopt value-based or policy-based reinforcement learning algorithms to train the model. We propose a heterogeneous MARL training framework, named QPMIX, which adopts a centralized training with distributed execution paradigm to enable heterogeneous agents to collaborate. Moreover, we theoretically prove the convergence of the proposed heterogeneous MARL method when using the linear value function approximation. Our method maximizes the network throughput and ensures fairness among stations, therefore, enhancing the overall network performance. Simulation results demonstrate that the proposed QPMIX algorithm improves throughput, mean delay, delay jitter, and collision rates compared with conventional carrier-sense multiple access with collision avoidance in the saturated traffic scenario. Furthermore, the QPMIX is shown to be robust in unsaturated and delay-sensitive traffic scenarios, and promotes cooperation among heterogeneous agents.

Organizing and managing cryptocurrency portfolios and decision-making on transactions is crucial in this market. Optimal selection of assets is one of the main challenges that requires accurate prediction of the price of cryptocurrencies. In this work, we categorize the financial time series into several similar subseries to increase prediction accuracy by learning each subseries category with similar behavior. For each category of the subseries, we create a deep learning model based on the attention mechanism to predict the next step of each subseries. Due to the limited amount of cryptocurrency data for training models, if the number of categories increases, the amount of training data for each model will decrease, and some complex models will not be trained well due to the large number of parameters. To overcome this challenge, we propose to combine the time series data of other cryptocurrencies to increase the amount of data for each category, hence increasing the accuracy of the models corresponding to each category.