Offloading computation to nearby edge/fog computing nodes, including the ones carried by moving vehicles, e.g., vehicular fog nodes (VFN), has proved to be a promising approach for enabling low-latency and compute-intensive mobility applications, such as cooperative and autonomous driving. This work considers vehicular fog computing scenarios where the clients of computation offloading services try to minimize their own costs while deciding which VFNs to offload their tasks. We focus on decentralized multi-agent decision-making in a repeated unknown game where each agent, e.g., service client, can observe only its own action and realized cost. In other words, each agent is unaware of the game composition or even the existence of opponents. We apply a completely uncoupled learning rule to generalize the decentralized decision-making algorithm presented in \cite{Cho2021} for the multi-agent case. The multi-agent solution proposed in this work can capture the unknown offloading cost variations susceptive to resource congestion under an adversarial framework where each agent may take implicit cost estimation and suitable resource choice adapting to the dynamics associated with volatile supply and demand. According to the evaluation via simulation, this work reveals that such individual perturbations for robustness to uncertainty and adaptation to dynamicity ensure a certain level of optimality in terms of social welfare, e.g., converging the actual sequence of play with unknown and asymmetric attributes and lowering the correspondent cost in social welfare due to the self-interested behaviors of agents.
相關內容
Decentralized stochastic gradient descent (D-SGD) allows collaborative learning on massive devices simultaneously without the control of a central server. However, existing theories claim that decentralization invariably undermines generalization. In this paper, we challenge the conventional belief and present a completely new perspective for understanding decentralized learning. We prove that D-SGD implicitly minimizes the loss function of an average-direction Sharpness-aware minimization (SAM) algorithm under general non-convex non-$\beta$-smooth settings. This surprising asymptotic equivalence reveals an intrinsic regularization-optimization trade-off and three advantages of decentralization: (1) there exists a free uncertainty evaluation mechanism in D-SGD to improve posterior estimation; (2) D-SGD exhibits a gradient smoothing effect; and (3) the sharpness regularization effect of D-SGD does not decrease as total batch size increases, which justifies the potential generalization benefit of D-SGD over centralized SGD (C-SGD) in large-batch scenarios.
Compliance with traffic laws is a fundamental requirement for human drivers on the road, and autonomous vehicles must adhere to traffic laws as well. However, current autonomous vehicles prioritize safety and collision avoidance primarily in their decision-making and planning, which will lead to misunderstandings and distrust from human drivers and may even result in accidents in mixed traffic flow. Therefore, ensuring the compliance of the autonomous driving decision-making system is essential for ensuring the safety of autonomous driving and promoting the widespread adoption of autonomous driving technology. To this end, the paper proposes a trigger-based layered compliance decision-making framework. This framework utilizes the decision intent at the highest level as a signal to activate an online violation monitor that identifies the type of violation committed by the vehicle. Then, a four-layer architecture for compliance decision-making is employed to generate compliantly trajectories. Using this system, autonomous vehicles can detect and correct potential violations in real-time, thereby enhancing safety and building public confidence in autonomous driving technology. Finally, the proposed method is evaluated on the DJI AD4CHE highway dataset under four typical highway scenarios: speed limit, following distance, overtaking, and lane-changing. The results indicate that the proposed method increases the vehicle's overall compliance rate from 13.85% to 84.46%, while reducing the proportion of active violations to 0%, demonstrating its effectiveness.
Community detection is a classic problem in network science with extensive applications in various fields. Among numerous approaches, the most common method is modularity maximization. Despite their design philosophy and wide adoption, heuristic modularity maximization algorithms rarely return an optimal partition or anything similar. We propose a specialized algorithm, Bayan, which returns partitions with a guarantee of either optimality or proximity to an optimal partition. At the core of the Bayan algorithm is a branch-and-cut scheme that solves an integer programming formulation of the modularity maximization problem to optimality or approximate it within a factor. We compare Bayan against 30 alternative community detection methods using structurally diverse synthetic and real networks. Our results demonstrate Bayan's distinctive accuracy and stability in retrieving ground-truth communities of standard benchmark graphs. Bayan is several times faster than open-source and commercial solvers for modularity maximization making it capable of finding optimal partitions for instances that cannot be optimized by any other existing method. Overall, our assessments point to Bayan as a suitable choice for exact maximization of modularity in real networks with up to 3000 edges (in their largest connected component) and approximating maximum modularity in larger instances on ordinary computers. A Python implementation of the Bayan algorithm (the bayanpy library) is publicly available through the package installer for Python (pip).
Traditional centralized multi-agent reinforcement learning (MARL) algorithms are sometimes unpractical in complicated applications, due to non-interactivity between agents, curse of dimensionality and computation complexity. Hence, several decentralized MARL algorithms are motivated. However, existing decentralized methods only handle the fully cooperative setting where massive information needs to be transmitted in training. The block coordinate gradient descent scheme they used for successive independent actor and critic steps can simplify the calculation, but it causes serious bias. In this paper, we propose a flexible fully decentralized actor-critic MARL framework, which can combine most of actor-critic methods, and handle large-scale general cooperative multi-agent setting. A primal-dual hybrid gradient descent type algorithm framework is designed to learn individual agents separately for decentralization. From the perspective of each agent, policy improvement and value evaluation are jointly optimized, which can stabilize multi-agent policy learning. Furthermore, our framework can achieve scalability and stability for large-scale environment and reduce information transmission, by the parameter sharing mechanism and a novel modeling-other-agents methods based on theory-of-mind and online supervised learning. Sufficient experiments in cooperative Multi-agent Particle Environment and StarCraft II show that our decentralized MARL instantiation algorithms perform competitively against conventional centralized and decentralized methods.
When agents collaborate on a task, it is important that they have some shared mental model of the task routines -- the set of feasible plans towards achieving the goals. However, in reality, situations often arise that such a shared mental model cannot be guaranteed, such as in ad-hoc teams where agents may follow different conventions or when contingent constraints arise that only some agents are aware of. Previous work on human-robot teaming has assumed that the team has a set of shared routines, which breaks down in these situations. In this work, we leverage epistemic logic to enable agents to understand the discrepancy in each other's beliefs about feasible plans and dynamically plan their actions to adapt or communicate to resolve the discrepancy. We propose a formalism that extends conditional doxastic logic to describe knowledge bases in order to explicitly represent agents' nested beliefs on the feasible plans and state of execution. We provide an online execution algorithm based on Monte Carlo Tree Search for the agent to plan its action, including communication actions to explain the feasibility of plans, announce intent, and ask questions. Finally, we evaluate the success rate and scalability of the algorithm and show that our agent is better equipped to work in teams without the guarantee of a shared mental model.
Neural networks, being susceptible to adversarial attacks, should face a strict level of scrutiny before being deployed in critical or adversarial applications. This paper uses ideas from Chaos Theory to explain, analyze, and quantify the degree to which neural networks are susceptible to or robust against adversarial attacks. To this end, we present a new metric, the "susceptibility ratio," given by $\hat \Psi(h, \theta)$, which captures how greatly a model's output will be changed by perturbations to a given input. Our results show that susceptibility to attack grows significantly with the depth of the model, which has safety implications for the design of neural networks for production environments. We provide experimental evidence of the relationship between $\hat \Psi$ and the post-attack accuracy of classification models, as well as a discussion of its application to tasks lacking hard decision boundaries. We also demonstrate how to quickly and easily approximate the certified robustness radii for extremely large models, which until now has been computationally infeasible to calculate directly.
Deep neural networks (DNNs) have succeeded in many different perception tasks, e.g., computer vision, natural language processing, reinforcement learning, etc. The high-performed DNNs heavily rely on intensive resource consumption. For example, training a DNN requires high dynamic memory, a large-scale dataset, and a large number of computations (a long training time); even inference with a DNN also demands a large amount of static storage, computations (a long inference time), and energy. Therefore, state-of-the-art DNNs are often deployed on a cloud server with a large number of super-computers, a high-bandwidth communication bus, a shared storage infrastructure, and a high power supplement. Recently, some new emerging intelligent applications, e.g., AR/VR, mobile assistants, Internet of Things, require us to deploy DNNs on resource-constrained edge devices. Compare to a cloud server, edge devices often have a rather small amount of resources. To deploy DNNs on edge devices, we need to reduce the size of DNNs, i.e., we target a better trade-off between resource consumption and model accuracy. In this dissertation, we studied four edge intelligence scenarios, i.e., Inference on Edge Devices, Adaptation on Edge Devices, Learning on Edge Devices, and Edge-Server Systems, and developed different methodologies to enable deep learning in each scenario. Since current DNNs are often over-parameterized, our goal is to find and reduce the redundancy of the DNNs in each scenario.
Automated Driving Systems (ADS) have made great achievements in recent years thanks to the efforts from both academia and industry. A typical ADS is composed of multiple modules, including sensing, perception, planning and control, which brings together the latest advances in multiple domains. Despite these achievements, safety assurance of the systems is still of great significance, since the unsafe behavior of ADS can bring catastrophic consequences and unacceptable economic and social losses. Testing is an important approach to system validation for the deployment in practice; in the context of ADS, it is extremely challenging, due to the system complexity and multidisciplinarity. There has been a great deal of literature that focuses on the testing of ADS, and a number of surveys have also emerged to summarize the technical advances. However, most of these surveys focus on the system-level testing that is performed within software simulators, and thereby ignore the distinct features of individual modules. In this paper, we provide a comprehensive survey on the existing ADS testing literature, which takes into account both module-level and system-level testing. Specifically, we make the following contributions: (1) we build a threat model that reveals the potential safety threats for each module of an ADS; (2) we survey the module-level testing techniques for ADS and highlight the technical differences affected by the properties of the modules; (3) we also survey the system-level testing techniques, but we focus on empirical studies that take a bird's-eye view on the system, the problems due to the collaborations between modules, and the gaps between ADS testing in simulators and real world; (4) we identify the challenges and opportunities in ADS testing, which facilitates the future research in this field.
In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale. In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5x better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.
Effective multi-robot teams require the ability to move to goals in complex environments in order to address real-world applications such as search and rescue. Multi-robot teams should be able to operate in a completely decentralized manner, with individual robot team members being capable of acting without explicit communication between neighbors. In this paper, we propose a novel game theoretic model that enables decentralized and communication-free navigation to a goal position. Robots each play their own distributed game by estimating the behavior of their local teammates in order to identify behaviors that move them in the direction of the goal, while also avoiding obstacles and maintaining team cohesion without collisions. We prove theoretically that generated actions approach a Nash equilibrium, which also corresponds to an optimal strategy identified for each robot. We show through extensive simulations that our approach enables decentralized and communication-free navigation by a multi-robot system to a goal position, and is able to avoid obstacles and collisions, maintain connectivity, and respond robustly to sensor noise.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191