Competitive Multi-armed Bandit Games for Resource Sharing

In modern resource-sharing systems, multiple agents access limited resources with unknown stochastic conditions to perform tasks. When multiple agents access the same resource (arm) simultaneously, they compete for successful usage, leading to contention and reduced rewards. This motivates our study of competitive multi-armed bandit (CMAB) games. In this paper, we study a new N-player K-arm competitive MAB game, where non-myopic players (agents) compete with each other to form diverse private estimations of unknown arms over time. Their possible collisions on same arms and time-varying nature of arm rewards make the policy analysis more involved than existing studies for myopic players. We explicitly analyze the threshold-based structures of social optimum and existing selfish policy, showing that the latter causes prolonged convergence time $\Omega(\frac{K}{\eta^2}\ln({\frac{KN}{\delta}}))$, while socially optimal policy with coordinated communication reduces it to $\mathcal{O}(\frac{K}{N\eta^2}\ln{(\frac{K}{\delta})})$. Based on the comparison, we prove that the competition among selfish players for the best arm can result in an infinite price of anarchy (PoA), indicating an arbitrarily large efficiency loss compared to social optimum. We further prove that no informational (non-monetary) mechanism (including Bayesian persuasion) can reduce the infinite PoA, as the strategic misreporting by non-myopic players undermines such approaches. To address this, we propose a Combined Informational and Side-Payment (CISP) mechanism, which provides socially optimal arm recommendations with proper informational and monetary incentives to players according to their time-varying private beliefs. Our CISP mechanism keeps ex-post budget balanced for social planner and ensures truthful reporting from players, achieving the minimum PoA=1 and same convergence time as social optimum.

To Analyze and Regulate Human-in-the-loop Learning for Congestion Games

In congestion games, selfish users behave myopically to crowd to the shortest paths, and the social planner designs mechanisms to regulate such selfish routing through information or payment incentives. However, such mechanism design requires the knowledge of time-varying traffic conditions and it is the users themselves to learn and report past road experiences to the social planner (e.g., Waze or Google Maps). When congestion games meet mobile crowdsourcing, it is critical to incentivize selfish users to explore non-shortest paths in the best exploitation-exploration trade-off. First, we consider a simple but fundamental parallel routing network with one deterministic path and multiple stochastic paths for users with an average arrival probability $\lambda$. We prove that the current myopic routing policy (widely used in Waze and Google Maps) misses both exploration (when strong hazard belief) and exploitation (when weak hazard belief) as compared to the social optimum. Due to the myopic policy's under-exploration, we prove that the caused price of anarchy (PoA) is larger than \(\frac{1}{1-\rho^{\frac{1}{\lambda}}}\), which can be arbitrarily large as discount factor \(\rho\rightarrow1\). To mitigate such huge efficiency loss, we propose a novel selective information disclosure (SID) mechanism: we only reveal the latest traffic information to users when they intend to over-explore stochastic paths upon arrival, while hiding such information when they want to under-explore. We prove that our mechanism successfully reduces PoA to be less than~\(2\). Besides the parallel routing network, we further extend our mechanism and PoA results to any linear path graphs with multiple intermediate nodes.

Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning

To improve the efficiency of warehousing system and meet huge customer orders, we aim to solve the challenges of dimension disaster and dynamic properties in hyper scale multi-robot task planning (MRTP) for robotic mobile fulfillment system (RMFS). Existing research indicates that hierarchical reinforcement learning (HRL) is an effective method to reduce these challenges. Based on that, we construct an efficient multi-stage HRL-based multi-robot task planner for hyper scale MRTP in RMFS, and the planning process is represented with a special temporal graph topology. To ensure optimality, the planner is designed with a centralized architecture, but it also brings the challenges of scaling up and generalization that require policies to maintain performance for various unlearned scales and maps. To tackle these difficulties, we first construct a hierarchical temporal attention network (HTAN) to ensure basic ability of handling inputs with unfixed lengths, and then design multi-stage curricula for hierarchical policy learning to further improve the scaling up and generalization ability while avoiding catastrophic forgetting. Additionally, we notice that policies with hierarchical structure suffer from unfair credit assignment that is similar to that in multi-agent reinforcement learning, inspired of which, we propose a hierarchical reinforcement learning algorithm with counterfactual rollout baseline to improve learning performance. Experimental results demonstrate that our planner outperform other state-of-the-art methods on various MRTP instances in both simulated and real-world RMFS. Also, our planner can successfully scale up to hyper scale MRTP instances in RMFS with up to 200 robots and 1000 retrieval racks on unlearned maps while keeping superior performance over other methods.

Theory of Mixture-of-Experts for Mobile Edge Computing

In mobile edge computing (MEC) networks, mobile users generate diverse machine learning tasks dynamically over time. These tasks are typically offloaded to the nearest available edge server, by considering communication and computational efficiency. However, its operation does not ensure that each server specializes in a specific type of tasks and leads to severe overfitting or catastrophic forgetting of previous tasks. To improve the continual learning (CL) performance of online tasks, we are the first to introduce mixture-of-experts (MoE) theory in MEC networks and save MEC operation from the increasing generalization error over time. Our MoE theory treats each MEC server as an expert and dynamically adapts to changes in server availability by considering data transfer and computation time. Unlike existing MoE models designed for offline tasks, ours is tailored for handling continuous streams of tasks in the MEC environment. We introduce an adaptive gating network in MEC to adaptively identify and route newly arrived tasks of unknown data distributions to available experts, enabling each expert to specialize in a specific type of tasks upon convergence. We derived the minimum number of experts required to match each task with a specialized, available expert. Our MoE approach consistently reduces the overall generalization error over time, unlike the traditional MEC approach. Interestingly, when the number of experts is sufficient to ensure convergence, adding more experts delays the convergence time and worsens the generalization error. Finally, we perform extensive experiments on real datasets in deep neural networks (DNNs) to verify our theoretical results.

NASM: Neural Anisotropic Surface Meshing

This paper introduces a new learning-based method, NASM, for anisotropic surface meshing. Our key idea is to propose a graph neural network to embed an input mesh into a high-dimensional (high-d) Euclidean embedding space to preserve curvature-based anisotropic metric by using a dot product loss between high-d edge vectors. This can dramatically reduce the computational time and increase the scalability. Then, we propose a novel feature-sensitive remeshing on the generated high-d embedding to automatically capture sharp geometric features. We define a high-d normal metric, and then derive an automatic differentiation on a high-d centroidal Voronoi tessellation (CVT) optimization with the normal metric to simultaneously preserve geometric features and curvature anisotropy that exhibit in the original 3D shapes. To our knowledge, this is the first time that a deep learning framework and a large dataset are proposed to construct a high-d Euclidean embedding space for 3D anisotropic surface meshing. Experimental results are evaluated and compared with the state-of-the-art in anisotropic surface meshing on a large number of surface models from Thingi10K dataset as well as tested on extensive unseen 3D shapes from Multi-Garment Network dataset and FAUST human dataset.

SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attention

Channel and spatial attentions have respectively brought significant improvements in extracting feature dependencies and spatial structure relations for various downstream vision tasks. While their combination is more beneficial for leveraging their individual strengths, the synergy between channel and spatial attentions has not been fully explored, lacking in fully harness the synergistic potential of multi-semantic information for feature guidance and mitigation of semantic disparities. Our study attempts to reveal the synergistic relationship between spatial and channel attention at multiple semantic levels, proposing a novel Spatial and Channel Synergistic Attention module (SCSA). Our SCSA consists of two parts: the Shareable Multi-Semantic Spatial Attention (SMSA) and the Progressive Channel-wise Self-Attention (PCSA). SMSA integrates multi-semantic information and utilizes a progressive compression strategy to inject discriminative spatial priors into PCSA's channel self-attention, effectively guiding channel recalibration. Additionally, the robust feature interactions based on the self-attention mechanism in PCSA further mitigate the disparities in multi-semantic information among different sub-features within SMSA. We conduct extensive experiments on seven benchmark datasets, including classification on ImageNet-1K, object detection on MSCOCO 2017, segmentation on ADE20K, and four other complex scene detection datasets. Our results demonstrate that our proposed SCSA not only surpasses the current state-of-the-art attention but also exhibits enhanced generalization capabilities across various task scenarios. The code and models are available at: https://github.com/HZAI-ZJNU/SCSA.

Theory on Mixture-of-Experts in Continual Learning

Continual learning (CL) has garnered significant attention because of its ability to adapt to new tasks that arrive over time. Catastrophic forgetting (of old tasks) has been identified as a major issue in CL, as the model adapts to new tasks. The Mixture-of-Experts (MoE) model has recently been shown to effectively mitigate catastrophic forgetting in CL, by employing a gating network to sparsify and distribute diverse tasks among multiple experts. However, there is a lack of theoretical analysis of MoE and its impact on the learning performance in CL. This paper provides the first theoretical results to characterize the impact of MoE in CL via the lens of overparameterized linear regression tasks. We establish the benefit of MoE over a single expert by proving that the MoE model can diversify its experts to specialize in different tasks, while its router learns to select the right expert for each task and balance the loads across all experts. Our study further suggests an intriguing fact that the MoE in CL needs to terminate the update of the gating network after sufficient training rounds to attain system convergence, which is not needed in the existing MoE studies that do not consider the continual task arrival. Furthermore, we provide explicit expressions for the expected forgetting and overall generalization error to characterize the benefit of MoE in the learning performance in CL. Interestingly, adding more experts requires additional rounds before convergence, which may not enhance the learning performance. Finally, we conduct experiments on both synthetic and real datasets to extend these insights from linear models to deep neural networks (DNNs), which also shed light on the practical algorithm design for MoE in CL.

Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models

Predicting the future trajectories of dynamic traffic actors is a cornerstone task in autonomous driving. Though existing notable efforts have resulted in impressive performance improvements, a gap persists in scene cognitive and understanding of the complex traffic semantics. This paper proposes Traj-LLM, the first to investigate the potential of using Large Language Models (LLMs) without explicit prompt engineering to generate future motion from agents' past/observed trajectories and scene semantics. Traj-LLM starts with sparse context joint coding to dissect the agent and scene features into a form that LLMs understand. On this basis, we innovatively explore LLMs' powerful comprehension abilities to capture a spectrum of high-level scene knowledge and interactive information. Emulating the human-like lane focus cognitive function and enhancing Traj-LLM's scene comprehension, we introduce lane-aware probabilistic learning powered by the pioneering Mamba module. Finally, a multi-modal Laplace decoder is designed to achieve scene-compliant multi-modal predictions. Extensive experiments manifest that Traj-LLM, fortified by LLMs' strong prior knowledge and understanding prowess, together with lane-aware probability learning, outstrips state-of-the-art methods across evaluation metrics. Moreover, the few-shot analysis further substantiates Traj-LLM's performance, wherein with just 50% of the dataset, it outperforms the majority of benchmarks relying on complete data utilization. This study explores equipping the trajectory prediction task with advanced capabilities inherent in LLMs, furnishing a more universal and adaptable solution for forecasting agent motion in a new way.

Human-in-the-loop Learning for Dynamic Congestion Games

Today mobile users learn and share their traffic observations via crowdsourcing platforms (e.g., Waze). Yet such platforms simply cater to selfish users' myopic interests to recommend the shortest path, and do not encourage enough users to travel and learn other paths for future others. Prior studies focus on one-shot congestion games without considering users' information learning, while our work studies how users learn and alter traffic conditions on stochastic paths in a human-in-the-loop manner. Our analysis shows that the myopic routing policy leads to severe under-exploration of stochastic paths. This results in a price of anarchy (PoA) greater than $2$, as compared to the socially optimal policy in minimizing the long-term social cost. Besides, the myopic policy fails to ensure the correct learning convergence about users' traffic hazard beliefs. To address this, we focus on informational (non-monetary) mechanisms as they are easier to implement than pricing. We first show that existing information-hiding mechanisms and deterministic path-recommendation mechanisms in Bayesian persuasion literature do not work with even (\text{PoA}=\infty). Accordingly, we propose a new combined hiding and probabilistic recommendation (CHAR) mechanism to hide all information from a selected user group and provide state-dependent probabilistic recommendations to the other user group. Our CHAR successfully ensures PoA less than (\frac{5}{4}), which cannot be further reduced by any other informational (non-monetary) mechanism. Besides the parallel network, we further extend our analysis and CHAR to more general linear path graphs with multiple intermediate nodes, and we prove that the PoA results remain unchanged. Additionally, we carry out experiments with real-world datasets to further extend our routing graphs and verify the close-to-optimal performance of our CHAR.

Path Planning Considering Time-Varying and Uncertain Movement Speed in Multi-Robot Automatic Warehouses: Problem Formulation and Algorithm

Path planning in the multi-robot system refers to calculating a set of actions for each robot, which will move each robot to its goal without conflicting with other robots. Lately, the research topic has received significant attention for its extensive applications, such as airport ground, drone swarms, and automatic warehouses. Despite these available research results, most of the existing investigations are concerned with the cases of robots with a fixed movement speed without considering uncertainty. Therefore, in this work, we study the problem of path-planning in the multi-robot automatic warehouse context, which considers the time-varying and uncertain robots' movement speed. Specifically, the path-planning module searches a path with as few conflicts as possible for a single agent by calculating traffic cost based on customarily distributed conflict probability and combining it with the classic A* algorithm. However, this probability-based method cannot eliminate all conflicts, and speed's uncertainty will constantly cause new conflicts. As a supplement, we propose the other two modules. The conflict detection and re-planning module chooses objects requiring re-planning paths from the agents involved in different types of conflicts periodically by our designed rules. Also, at each step, the scheduling module fills up the agent's preserved queue and decides who has a higher priority when the same element is assigned to two agents simultaneously. Finally, we compare the proposed algorithm with other algorithms from academia and industry, and the results show that the proposed method is validated as the best performance.