arXiv subjects

Runyu Zhang

Publications and source records attributed to Runyu Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Survey

Traffic Surveillance Systems (TSS) have become increasingly crucial in modern intelligent transportation systems, with vision technologies playing a central role for scene perception and understanding. While existing surveys typically focus on isolated aspects of TSS, a comprehensive analytical framework bridging low-level and high-level perception tasks, particularly considering emerging technologies, remains lacking. This paper presents a systematic review of vision technologies in TSS, examining both low-level perception tasks (object detection, classification, and tracking) and high-level perception tasks (parameter estimation, anomaly detection, and behavior understanding). Specifically, we first provide a detailed methodological categorization and comprehensive performance evaluation for each task. Our investigation reveals five fundamental limitations in current TSS: perceptual data degradation in complex scenarios, data-driven learning constraints, semantic understanding gaps, sensing coverage limitations and computational resource demands. To address these challenges, we systematically analyze five categories of current approaches and potential trends: advanced perception enhancement, efficient learning paradigms, knowledge-enhanced understanding, cooperative sensing frameworks and efficient computing frameworks, critically assessing their real-world applicability. Furthermore, we evaluate the transformative potential of foundation models in TSS, which exhibit remarkable zero-shot learning abilities, strong generalization, and sophisticated reasoning capabilities across diverse tasks. This review provides a unified analytical framework bridging low-level and high-level perception tasks, systematically analyzes current limitations and solutions, and presents a structured roadmap for integrating emerging technologies, particularly foundation models, to enhance TSS capabilities.

cs.CV↗

arXiv2024

Scalable spectral representations for multi-agent reinforcement learning in network MDPs

Network Markov Decision Processes (MDPs), a popular model for multi-agent control, pose a significant challenge to efficient learning due to the exponential growth of the global state-action space with the number of agents. In this work, utilizing the exponential decay property of network dynamics, we first derive scalable spectral local representations for network MDPs, which induces a network linear subspace for the local $Q$-function of each agent. Building on these local spectral representations, we design a scalable algorithmic framework for continuous state-action network MDPs, and provide end-to-end guarantees for the convergence of our algorithm. Empirically, we validate the effectiveness of our scalable representation-based approach on two benchmark problems, and demonstrate the advantages of our approach over generic function approximation approaches to representing the local $Q$-functions.

cs.MA↗

arXiv2024

Soft Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity

Robust Markov Decision Processes (MDPs) and risk-sensitive MDPs are both powerful tools for making decisions in the presence of uncertainties. Previous efforts have aimed to establish their connections, revealing equivalences in specific formulations. This paper introduces a new formulation for risk-sensitive MDPs, which assesses risk in a slightly different manner compared to the classical Markov risk measure (Ruszczyński 2010), and establishes its equivalence with a class of soft robust MDP (RMDP) problems, including the standard RMDP as a special case. Leveraging this equivalence, we further derive the policy gradient theorem for both problems, proving gradient domination and global convergence of the exact policy gradient method under the tabular setting with direct parameterization. This forms a sharp contrast to the Markov risk measure, known to be potentially non-gradient-dominant (Huang et al. 2021). We also propose a sample-based offline learning algorithm, namely the robust fitted-Z iteration (RFZI), for a specific soft RMDP problem with a KL-divergence regularization term (or equivalently the risk-sensitive MDP with an entropy risk measure). We showcase its streamlined design and less stringent assumptions due to the equivalence and analyze its sample complexity

math.OC↗

arXiv2024

Multi-Agent Coverage Control with Transient Behavior Consideration

This paper studies the multi-agent coverage control (MAC) problem where agents must dynamically learn an unknown density function while performing coverage tasks. Unlike many current theoretical frameworks that concentrate solely on the regret occurring at specific targeted sensory locations, our approach additionally considers the regret caused by transient behavior - the path from one location and another. We propose the multi-agent coverage control with the doubling trick (MAC-DT) algorithm and demonstrate that it achieves (approximated) regret of $\widetilde{O}(\sqrt{T})$ even when accounting for the transient behavior. Our result is also supported by numerical experiments, showcasing that the proposed algorithm manages to match or even outperform the baseline algorithms in simulation environments. We also show how our algorithm can be modified to handle safety constraints and further implement the algorithm on a real-robotic testbed.

math.OC↗

arXiv2024

Cooperative Multi-Agent Graph Bandits: UCB Algorithm and Regret Analysis

In this paper, we formulate the multi-agent graph bandit problem as a multi-agent extension of the graph bandit problem introduced by Zhang, Johansson, and Li [CISS 57, 1-6 (2023)]. In our formulation, $N$ cooperative agents travel on a connected graph $G$ with $K$ nodes. Upon arrival at each node, agents observe a random reward drawn from a node-dependent probability distribution. The reward of the system is modeled as a weighted sum of the rewards the agents observe, where the weights capture some transformation of the reward associated with multiple agents sampling the same node at the same time. We propose an Upper Confidence Bound (UCB)-based learning algorithm, Multi-G-UCB, and prove that its expected regret over $T$ steps is bounded by $O(γN\log(T)[\sqrt{KT} + DK])$, where $D$ is the diameter of graph $G$ and $γ$ a boundedness parameter associated with the weight functions. Lastly, we numerically test our algorithm by comparing it to alternative methods.

cs.LG↗

arXiv2024

Scalable Reinforcement Learning for Linear-Quadratic Control of Networks

Distributed optimal control is known to be challenging and can become intractable even for linear-quadratic regulator problems. In this work, we study a special class of such problems where distributed state feedback controllers can give near-optimal performance. More specifically, we consider networked linear-quadratic controllers with decoupled costs and spatially exponentially decaying dynamics. We aim to exploit the structure in the problem to design a scalable reinforcement learning algorithm for learning a distributed controller. Recent work has shown that the optimal controller can be well approximated only using information from a $κ$-neighborhood of each agent. Motivated by these results, we show that similar results hold for the agents' individual value and Q-functions. We continue by designing an algorithm, based on the actor-critic framework, to learn distributed controllers only using local information. Specifically, the Q-function is estimated by modifying the Least Squares Temporal Difference for Q-functions method to only use local information. The algorithm then updates the policy using gradient descent. Finally, we evaluate the algorithm through simulations that indeed suggest near-optimal performance.

eess.SY↗

arXiv2023

Gradient play in stochastic games: stationary points, convergence, and sample complexity

We study the performance of the gradient play algorithm for stochastic games (SGs), where each agent tries to maximize its own total discounted reward by making decisions independently based on current state information which is shared between agents. Policies are directly parameterized by the probability of choosing a certain action at a given state. We show that Nash equilibria (NEs) and first-order stationary policies are equivalent in this setting, and give a local convergence rate around strict NEs. Further, for a subclass of SGs called Markov potential games (which includes the setting with identical rewards as an important special case), we design a sample-based reinforcement learning algorithm and give a non-asymptotic global convergence rate analysis for both exact gradient play and our sample-based learning algorithm. Our result shows that the number of iterations to reach an $ε$-NE scales linearly, instead of exponentially, with the number of agents. Local geometry and local stability are also considered, where we prove that strict NEs are local maxima of the total potential function and fully-mixed NEs are saddle points.

cs.LG↗

arXiv2023

Multi-Agent Reinforcement Learning with Reward Delays

This paper considers multi-agent reinforcement learning (MARL) where the rewards are received after delays and the delay time varies across agents and across time steps. Based on the V-learning framework, this paper proposes MARL algorithms that efficiently deal with reward delays. When the delays are finite, our algorithm reaches a coarse correlated equilibrium (CCE) with rate $\tilde{\mathcal{O}}(\frac{H^3\sqrt{S\mathcal{T}_K}}{K}+\frac{H^3\sqrt{SA}}{\sqrt{K}})$ where $K$ is the number of episodes, $H$ is the planning horizon, $S$ is the size of the state space, $A$ is the size of the largest action space, and $\mathcal{T}_K$ is the measure of total delay formally defined in the paper. Moreover, our algorithm is extended to cases with infinite delays through a reward skipping scheme. It achieves convergence rate similar to the finite delay case.

cs.MA↗

arXiv2023

On the Optimal Control of Network LQR with Spatially-Exponential Decaying Structure

This paper studies network LQR problems with system matrices being spatially-exponential decaying (SED) between nodes in the network. The major objective is to study whether the optimal controller also enjoys a SED structure, which is an appealing property for ensuring the optimality of decentralized control over the network. We start with studying the open-loop asymptotically stable system and show that the optimal LQR state feedback gain $K$ is `quasi'-SED in this setting, i.e. $\|[K]_{ij}\|\sim O\left(e^{-\frac{c}{\mathrm{poly}\ln(N)}}\mathrm{dist}(i,j)\right)$. The decaying rate $c$ depends on the decaying rate and norms of system matrices and the open-loop exponential stability constants. Then the result is further generalized to unstable systems under a SED stabilizability assumption. Building upon the `quasi'-SED result on $K$, we give an upper-bound on the performance of $κ$-truncated local controllers, suggesting that distributed controllers can achieve near-optimal performance for SED systems. We develop these results via studying the structure of another type of controller, disturbance response control, which has been studied and used in recent online control literature; thus as a side result, we also prove the `quasi'-SED property of the optimal disturbance response control, which serves as a contribution on its own merit.

math.OC↗

arXiv2023

On the Relationship of Optimal State Feedback and Disturbance Response Controllers

This paper studies the relationship between state feedback policies and disturbance response policies for the standard Linear Quadratic Regulator (LQR). For open-loop stable plants, we establish a simple relationship between the optimal state feedback controller $u_t=K_\star x_t$ and the optimal disturbance response controller $u_t=L^{(H)}_{\star;1}w_{t-1}+\cdots+L^{(H)}_{\star;H}w_{t-H}$ with $H$-order. Here $x_t, w_t, u_t$ stands for the state, disturbance, control action of the system, respectively. Our result shows that $L_{\star,1}^{(H)}$ is a good approximation of $K_\star$ and the approximation error $\|K_\star - L_{\star,1}^{(H)}\|$ decays exponentially with $H$. We further extend this result to LQR for open-loop unstable systems, when a pre-stabilizing controller $K_0$ is available.

math.OC↗

arXiv2023

Markov Games with Decoupled Dynamics: Price of Anarchy and Sample Complexity

This paper studies the finite-time horizon Markov games where the agents' dynamics are decoupled but the rewards can possibly be coupled across agents. The policy class is restricted to local policies where agents make decisions using their local state. We first introduce the notion of smooth Markov games which extends the smoothness argument for normal form games to our setting, and leverage the smoothness property to bound the price of anarchy of the Markov game. For a specific type of Markov game called the Markov potential game, we also develop a distributed learning algorithm, multi-agent soft policy iteration (MA-SPI), which provably converges to a Nash equilibrium. Sample complexity of the algorithm is also provided. Lastly, our results are validated using a dynamic covering game.

cs.GT↗

arXiv2023

Neural Nonnegative Matrix Factorization for Hierarchical Multilayer Topic Modeling

We introduce a new method based on nonnegative matrix factorization, Neural NMF, for detecting latent hierarchical structure in data. Datasets with hierarchical structure arise in a wide variety of fields, such as document classification, image processing, and bioinformatics. Neural NMF recursively applies NMF in layers to discover overarching topics encompassing the lower-level features. We derive a backpropagation optimization scheme that allows us to frame hierarchical NMF as a neural network. We test Neural NMF on a synthetic hierarchical dataset, the 20 Newsgroups dataset, and the MyLymeData symptoms dataset. Numerical results demonstrate that Neural NMF outperforms other hierarchical NMF methods on these data sets and offers better learned hierarchical structure and interpretability of topics.

cs.LG↗

arXiv2022

On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games

Softmax policy gradient is a popular algorithm for policy optimization in single-agent reinforcement learning, particularly since projection is not needed for each gradient update. However, in multi-agent systems, the lack of central coordination introduces significant additional difficulties in the convergence analysis. Even for a stochastic game with identical interest, there can be multiple Nash Equilibria (NEs), which disables proof techniques that rely on the existence of a unique global optimum. Moreover, the softmax parameterization introduces non-NE policies with zero gradient, making it difficult for gradient-based algorithms in seeking NEs. In this paper, we study the finite time convergence of decentralized softmax gradient play in a special form of game, Markov Potential Games (MPGs), which includes the identical interest game as a special case. We investigate both gradient play and natural gradient play, with and without $\log$-barrier regularization. The established convergence rates for the unregularized cases contain a trajectory-dependent constant that can be arbitrarily large, whereas the $\log$-barrier regularization overcomes this drawback, with the cost of slightly worse dependence on other factors such as the action set size. An empirical study on an identical interest matrix game confirms the theoretical findings.

math.OC↗

arXiv2022

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

This paper studies policy optimization algorithms for multi-agent reinforcement learning. We begin by proposing an algorithm framework for two-player zero-sum Markov Games in the full-information setting, where each iteration consists of a policy update step at each state using a certain matrix game algorithm, and a value update step with a certain learning rate. This framework unifies many existing and new policy optimization algorithms. We show that the state-wise average policy of this algorithm converges to an approximate Nash equilibrium (NE) of the game, as long as the matrix game algorithms achieve low weighted regret at each state, with respect to weights determined by the speed of the value updates. Next, we show that this framework instantiated with the Optimistic Follow-The-Regularized-Leader (OFTRL) algorithm at each state (and smooth value updates) can find an $\mathcal{\widetilde{O}}(T^{-5/6})$ approximate NE in $T$ iterations, and a similar algorithm with slightly modified value update rule achieves a faster $\mathcal{\widetilde{O}}(T^{-1})$ convergence rate. These improve over the current best $\mathcal{\widetilde{O}}(T^{-1/2})$ rate of symmetric policy optimization type algorithms. We also extend this algorithm to multi-player general-sum Markov Games and show an $\mathcal{\widetilde{O}}(T^{-3/4})$ convergence rate to Coarse Correlated Equilibria (CCE). Finally, we provide a numerical example to verify our theory and investigate the importance of smooth value updates, and find that using "eager" value updates instead (equivalent to the independent natural policy gradient algorithm) may significantly slow down the convergence, even on a simple game with $H=2$ layers.

cs.LG↗

arXiv2021

On the Regret Analysis of Online LQR Control with Predictions

In this paper, we study the dynamic regret of online linear quadratic regulator (LQR) control with time-varying cost functions and disturbances. We consider the case where a finite look-ahead window of cost functions and disturbances is available at each stage. The online control algorithm studied in this paper falls into the category of model predictive control (MPC) with a particular choice of terminal costs to ensure the exponential stability of MPC. It is proved that the regret of such an online algorithm decays exponentially fast with the length of predictions. The impact of inaccurate prediction on disturbances is also investigated in this paper.

math.OC↗

arXiv2020

Distributed Reinforcement Learning for Decentralized Linear Quadratic Control: A Derivative-Free Policy Optimization Approach

This paper considers a distributed reinforcement learning problem for decentralized linear quadratic control with partial state observations and local costs. We propose a Zero-Order Distributed Policy Optimization algorithm (ZODPO) that learns linear local controllers in a distributed fashion, leveraging the ideas of policy gradient, zero-order optimization and consensus algorithms. In ZODPO, each agent estimates the global cost by consensus, and then conducts local policy gradient in parallel based on zero-order gradient estimation. ZODPO only requires limited communication and storage even in large-scale systems. Further, we investigate the nonasymptotic performance of ZODPO and show that the sample complexity to approach a stationary point is polynomial with the error tolerance's inverse and the problem dimensions, demonstrating the scalability of ZODPO. We also show that the controllers generated throughout ZODPO are stabilizing controllers with high probability. Lastly, we numerically test ZODPO on multi-zone HVAC systems.

eess.SY↗

arXiv2020

An Efficient and Wear-Leveling-Aware Frequent-Pattern Mining on Non-Volatile Memory

Frequent-pattern mining is a common approach to reveal the valuable hidden trends behind data. However, existing frequent-pattern mining algorithms are designed for DRAM, instead of persistent memories (PMs), which can lead to severe performance and energy overhead due to the utterly different characteristics between DRAM and PMs when they are running on PMs. In this paper, we propose an efficient and Wear-leveling-aware Frequent-Pattern Mining scheme, WFPM, to solve this problem. The proposed WFPM is evaluated by a series of experiments based on realistic datasets from diversified application scenarios, where WFPM achieves 32.0% performance improvement and prolongs the NVM lifetime of header table by 7.4x over the EvFP-Tree.

cs.DB↗

arXiv2019

Reconstruct the Directories for In-Memory File Systems

Existing path lookup routines in file systems need to construct an auxiliary index in memory or traverse the dentries of the directory file sequentially, which brings either heavy writes or large timing cost. This paper designs a novel path lookup mechanism, Content-Indexed Browsing (CIB), for file systems on persistent memory, in which the structure of directory files is an exclusive index that can be searched in $O(log(n))$ time. We implement CIB in a real persistent memory file system, PMFS, denoted by CIB-PMFS. Comprehensive evaluations show that CIB can achieve times of performance improvement over the conventional lookup schemes in PMFS, and brings 20.4\% improvement on the overall performance of PMFS. Furthermore, CIB reduces the writes on persistent memory by orders of magnitude comparing with existing extra index schemes.

cs.DC↗