As machine learning (ML) models are increasingly used in social domains to make consequential decisions about humans, they often have the power to reshape data distributions. Humans, as strategic agents, continuously adapt their behaviors in response to the learning system. As populations change dynamically, ML systems may need frequent updates to ensure high performance. However, acquiring high-quality human-annotated samples can be highly challenging and even infeasible in social domains. A common practice to address this issue is using the model itself to annotate unlabeled data samples. This paper investigates the long-term impacts when ML models are retrained with model-annotated samples when they incorporate human strategic responses. We first formalize the interactions between strategic agents and the model and then analyze how they evolve under such dynamic interactions. We find that agents are increasingly likely to receive positive decisions as the model gets retrained, whereas the proportion of agents with positive labels may decrease over time. We thus propose a refined retraining process to stabilize the dynamics. Last, we examine how algorithmic fairness can be affected by these retraining processes and find that enforcing common fairness constraints at every round may not benefit the disadvantaged group in the long run. Experiments on (semi-)synthetic and real data validate the theoretical findings.

Multi-Robot-Arm Motion Planning (M-RAMP) is a challenging problem featuring complex single-agent planning and multi-agent coordination. Recent advancements in extending the popular Conflict-Based Search (CBS) algorithm have made large strides in solving Multi-Agent Path Finding (MAPF) problems. However, fundamental challenges remain in applying CBS to M-RAMP. A core challenge is the existing reliance of the CBS framework on conservative "complete" constraints. These constraints ensure solution guarantees but often result in slow pruning of the search space -- causing repeated expensive single-agent planning calls. Therefore, even though it is possible to leverage domain knowledge and design incomplete M-RAMP-specific CBS constraints to more efficiently prune the search, using these constraints would render the algorithm itself incomplete. This forces practitioners to choose between efficiency and completeness. In light of these challenges, we propose a novel algorithm, Generalized ECBS, aimed at removing the burden of choice between completeness and efficiency in MAPF algorithms. Our approach enables the use of arbitrary constraints in conflict-based algorithms while preserving completeness and bounding sub-optimality. This enables practitioners to capitalize on the benefits of arbitrary constraints and opens a new space for constraint design in MAPF that has not been explored. We provide a theoretical analysis of our algorithms, propose new "incomplete" constraints, and demonstrate their effectiveness through experiments in M-RAMP.

Cooperative Adaptive Cruise Control (CACC) represents a quintessential control strategy for orchestrating vehicular platoon movement within Connected and Automated Vehicle (CAV) systems, significantly enhancing traffic efficiency and reducing energy consumption. In recent years, the data-driven methods, such as reinforcement learning (RL), have been employed to address this task due to their significant advantages in terms of efficiency and flexibility. However, the delay issue, which often arises in real-world CACC systems, is rarely taken into account by current RL-based approaches. To tackle this problem, we propose a Delay-Aware Multi-Agent Reinforcement Learning (DAMARL) framework aimed at achieving safe and stable control for CACC. We model the entire decision-making process using a Multi-Agent Delay-Aware Markov Decision Process (MADA-MDP) and develop a centralized training with decentralized execution (CTDE) MARL framework for distributed control of CACC platoons. An attention mechanism-integrated policy network is introduced to enhance the performance of CAV communication and decision-making. Additionally, a velocity optimization model-based action filter is incorporated to further ensure the stability of the platoon. Experimental results across various delay conditions and platoon sizes demonstrate that our approach consistently outperforms baseline methods in terms of platoon safety, stability and overall performance.

We present a novel framework for addressing the challenges of multi-Agent planning and formation control within intricate and dynamic environments. This framework transforms the Multi-Agent Path Finding (MAPF) problem into a Multi-Agent Trajectory Planning (MATP) problem. Unlike traditional MAPF solutions, our multilayer optimization scheme consists of a global planner optimization solver, which is dedicated to determining concise global paths for each individual robot, and a local planner with an embedded optimization solver aimed at ensuring the feasibility of local robot trajectories. By implementing a hierarchical prioritization strategy, we enhance robots' efficiency and approximate the global optimal solution. Specifically, within the global planner, we employ the Augmented Graph Search (AGS) algorithm, which significantly improves the speed of solutions. Meanwhile, within the local planner optimization solver, we utilize Control Barrier functions (CBFs) and introduced an oblique cylindrical obstacle bounding box based on the time axis for obstacle avoidance and construct a single-robot locally aware-communication circle to ensure the simplicity, speed, and accuracy of locally optimized solutions. Additionally, we integrate the weight and priority of path traces to prevent deadlocks in limiting scenarios. Compared to the other state-of-the-art methods, including CBS, ECBS and other derivative algorithms, our proposed method demonstrates superior performance in terms of capacity, flexible scalability and overall task optimality in theory, as validated through simulations and experiments.

The exploration of high-speed movement by robots or road traffic agents is crucial for autonomous driving and navigation. Trajectory prediction at high speeds requires considering historical features and interactions with surrounding entities, a complexity not as pronounced in lower-speed environments. Prior methods have assessed the spatio-temporal dynamics of agents but often neglected intrinsic intent and uncertainty, thereby limiting their effectiveness. We present the Denoised Endpoint Distribution model for trajectory prediction, which distinctively models agents' spatio-temporal features alongside their intrinsic intentions and uncertainties. By employing Diffusion and Transformer models to focus on agent endpoints rather than entire trajectories, our approach significantly reduces model complexity and enhances performance through endpoint information. Our experiments on open datasets, coupled with comparison and ablation studies, demonstrate our model's efficacy and the importance of its components. This approach advances trajectory prediction in high-speed scenarios and lays groundwork for future developments.

While our understanding of fairness in machine learning has significantly progressed, our understanding of fairness in reinforcement learning (RL) remains nascent. Most of the attention has been on fairness in one-shot classification tasks; however, real-world, RL-enabled systems (e.g., autonomous vehicles) are much more complicated in that agents operate in dynamic environments over a long period of time. To ensure the responsible development and deployment of these systems, we must better understand fairness in RL. In this paper, we survey the literature to provide the most up-to-date snapshot of the frontiers of fairness in RL. We start by reviewing where fairness considerations can arise in RL, then discuss the various definitions of fairness in RL that have been put forth thus far. We continue to highlight the methodologies researchers used to implement fairness in single- and multi-agent RL systems before showcasing the distinct application domains that fair RL has been investigated in. Finally, we critically examine gaps in the literature, such as understanding fairness in the context of RLHF, that still need to be addressed in future work to truly operationalize fair RL in real-world systems.

In automated user interactive design, designers face key challenges, including accurate representation of user intent, crafting high-quality components, and ensuring both aesthetic and semantic consistency. Addressing these challenges, we introduce MAxPrototyper, our human-centered, multi-agent system for interactive design generation. The core of MAxPrototyper is a theme design agent. It coordinates with specialized sub-agents, each responsible for generating specific parts of the design. Through an intuitive online interface, users can control the design process by providing text descriptions and layout. Enhanced by improved language and image generation models, MAxPrototyper generates each component with careful detail and contextual understanding. Its multi-agent architecture enables a multi-round interaction capability between the system and users, facilitating precise and customized design adjustments throughout the creation process.

Cooperative Multi-Agent Reinforcement Learning (MARL) necessitates seamless collaboration among agents, often represented by an underlying relation graph. Existing methods for learning this graph primarily focus on agent-pair relations, neglecting higher-order relationships. While several approaches attempt to extend cooperation modelling to encompass behaviour similarities within groups, they commonly fall short in concurrently learning the latent graph, thereby constraining the information exchange among partially observed agents. To overcome these limitations, we present a novel approach to infer the Group-Aware Coordination Graph (GACG), which is designed to capture both the cooperation between agent pairs based on current observations and group-level dependencies from behaviour patterns observed across trajectories. This graph is further used in graph convolution for information exchange between agents during decision-making. To further ensure behavioural consistency among agents within the same group, we introduce a group distance loss, which promotes group cohesion and encourages specialization between groups. Our evaluations, conducted on StarCraft II micromanagement tasks, demonstrate GACG's superior performance. An ablation study further provides experimental evidence of the effectiveness of each component of our method.

Generative document retrieval, an emerging paradigm in information retrieval, learns to build connections between documents and identifiers within a single model, garnering significant attention. However, there are still two challenges: (1) neglecting inner-content correlation during document representation; (2) lacking explicit semantic structure during identifier construction. Nonetheless, events have enriched relations and well-defined taxonomy, which could facilitate addressing the above two challenges. Inspired by this, we propose Event GDR, an event-centric generative document retrieval model, integrating event knowledge into this task. Specifically, we utilize an exchange-then-reflection method based on multi-agents for event knowledge extraction. For document representation, we employ events and relations to model the document to guarantee the comprehensiveness and inner-content correlation. For identifier construction, we map the events to well-defined event taxonomy to construct the identifiers with explicit semantic structure. Our method achieves significant improvement over the baselines on two datasets, and also hopes to provide insights for future research.

Robotics has been a popular field of research in the past few decades, with much success in industrial applications such as manufacturing and logistics. This success is led by clearly defined use cases and controlled operating environments. However, robotics has yet to make a large impact in domestic settings. This is due in part to the difficulty and complexity of designing mass-manufactured robots that can succeed in the variety of homes and environments that humans live in and that can operate safely in close proximity to humans. This paper explores the use of contextual affordances to enable safe exploration and learning in robotic scenarios targeted in the home. In particular, we propose a simple state representation that allows us to extend contextual affordances to larger state spaces and showcase how affordances can improve the success and convergence rate of a reinforcement learning algorithm in simulation. Our results suggest that after further iterations, it is possible to consider the implementation of this approach in a real robot manipulator. Furthermore, in the long term, this work could be the foundation for future explorations of human-robot interactions in complex domestic environments. This could be possible once state-of-the-art robot manipulators achieve the required level of dexterity for the described affordances in this paper.