Emergence, a global property of complex adaptive systems (CASs) constituted by interactive agents, is prevalent in real-world dynamic systems, e.g., network-level traffic congestions. Detecting its formation and evaporation helps to monitor the state of a system, allowing to issue a warning signal for harmful emergent phenomena. Since there is no centralized controller of CAS, detecting emergence based on each agent's local observation is desirable but challenging. Existing works are unable to capture emergence-related spatial patterns, and fail to model the nonlinear relationships among agents. This paper proposes a hierarchical framework with spatio-temporal consistency learning to solve these two problems by learning the system representation and agent representations, respectively. Especially, spatio-temporal encoders are tailored to capture agents' nonlinear relationships and the system's complex evolution. Representations of the agents and the system are learned by preserving the intrinsic spatio-temporal consistency in a self-supervised manner. Our method achieves more accurate detection than traditional methods and deep learning methods on three datasets with well-known yet hard-to-detect emergent behaviors. Notably, our hierarchical framework is generic, which can employ other deep learning methods for agent-level and system-level detection.
相關內容
We consider the task of estimating a structural model of dynamic decisions by a human agent based upon the observable history of implemented actions and visited states. This problem has an inherent nested structure: in the inner problem, an optimal policy for a given reward function is identified while in the outer problem, a measure of fit is maximized. Several approaches have been proposed to alleviate the computational burden of this nested-loop structure, but these methods still suffer from high complexity when the state space is either discrete with large cardinality or continuous in high dimensions. Other approaches in the inverse reinforcement learning (IRL) literature emphasize policy estimation at the expense of reduced reward estimation accuracy. In this paper we propose a single-loop estimation algorithm with finite time guarantees that is equipped to deal with high-dimensional state spaces without compromising reward estimation accuracy. In the proposed algorithm, each policy improvement step is followed by a stochastic gradient step for likelihood maximization. We show that the proposed algorithm converges to a stationary solution with a finite-time guarantee. Further, if the reward is parameterized linearly, we show that the algorithm approximates the maximum likelihood estimator sublinearly. Finally, by using robotics control problems in MuJoCo and their transfer settings, we show that the proposed algorithm achieves superior performance compared with other IRL and imitation learning benchmarks.
We propose a new and generic approach for detecting multiple change-points in general dependent data, termed random interval distillation (RID). By collecting random intervals with sufficient strength of signals and reassembling them into a sequence of informative short intervals, our new approach captures the shifts in signal characteristics across diverse dependent data forms including locally stationary high-dimensional time series and dynamic networks with Markov formation. We further propose a range of secondary refinements tailored to various data types to enhance the localization precision. Notably, for univariate time series and low-rank autoregressive networks, our methods achieve the minimax optimality as their independent counterparts. For practical applications, we introduce a clustering-based and data-driven procedure to determine the optimal threshold for signal strength, which is adaptable to a wide array of dependent data scenarios utilizing the connection between RID and clustering. Additionally, our method has been extended to identify kinks and changes in signals characterized by piecewise polynomial trends. We examine the effectiveness and usefulness of our methodology via extensive simulation studies and a real data example, implementing it in the R-package rid.
Due to its high sample complexity, simulation is, as of today, critical for the successful application of reinforcement learning. Many real-world problems, however, exhibit overly complex dynamics, which makes their full-scale simulation computationally slow. In this paper, we show how to decompose large networked systems of many agents into multiple local components such that we can build separate simulators that run independently and in parallel. To monitor the influence that the different local components exert on one another, each of these simulators is equipped with a learned model that is periodically trained on real trajectories. Our empirical results reveal that distributing the simulation among different processes not only makes it possible to train large multi-agent systems in just a few hours but also helps mitigate the negative effects of simultaneous learning.
Autonomous assistance of people with motor impairments is one of the most promising applications of autonomous robotic systems. Recent studies have reported encouraging results using deep reinforcement learning (RL) in the healthcare domain. Previous studies showed that assistive tasks can be formulated as multi-agent RL, wherein there are two agents: a caregiver and a care-receiver. However, policies trained in multi-agent RL are often sensitive to the policies of other agents. In such a case, a trained caregiver's policy may not work for different care-receivers. To alleviate this issue, we propose a framework that learns a robust caregiver's policy by training it for diverse care-receiver responses. In our framework, diverse care-receiver responses are autonomously learned through trials and errors. In addition, to robustify the care-giver's policy, we propose a strategy for sampling a care-receiver's response in an adversarial manner during the training. We evaluated the proposed method using tasks in an Assistive Gym. We demonstrate that policies trained with a popular deep RL method are vulnerable to changes in policies of other agents and that the proposed framework improves the robustness against such changes.
The growing integration of large language models (LLMs) into social operations amplifies their impact on decisions in crucial areas such as economics, law, education, and healthcare, raising public concerns about these models' discrimination-related safety and reliability. However, prior discrimination measuring frameworks solely assess the average discriminatory behavior of LLMs, often proving inadequate due to the overlook of an additional discrimination-leading factor, i.e., the LLMs' prediction variation across diverse contexts. In this work, we present the Prejudice-Caprice Framework (PCF) that comprehensively measures discrimination in LLMs by considering both their consistently biased preference and preference variation across diverse contexts. Specifically, we mathematically dissect the aggregated contextualized discrimination risk of LLMs into prejudice risk, originating from LLMs' persistent prejudice, and caprice risk, stemming from their generation inconsistency. In addition, we utilize a data-mining approach to gather preference-detecting probes from sentence skeletons, devoid of attribute indications, to approximate LLMs' applied contexts. While initially intended for assessing discrimination in LLMs, our proposed PCF facilitates the comprehensive and flexible measurement of any inductive biases, including knowledge alongside prejudice, across various modality models. We apply our discrimination-measuring framework to 12 common LLMs, yielding intriguing findings: i) modern LLMs demonstrate significant pro-male stereotypes, ii) LLMs' exhibited discrimination correlates with several social and economic factors, iii) prejudice risk dominates the overall discrimination risk and follows a normal distribution, and iv) caprice risk contributes minimally to the overall risk but follows a fat-tailed distribution, suggesting that it is wild risk requiring enhanced surveillance.
Latent variable models are increasingly used in economics for high-dimensional categorical data like text and surveys. We demonstrate the effectiveness of Hamiltonian Monte Carlo (HMC) with parallelized automatic differentiation for analyzing such data in a computationally efficient and methodologically sound manner. Our new model, Supervised Topic Model with Covariates, shows that carefully modeling this type of data can have significant implications on conclusions compared to a simpler, frequently used, yet methodologically problematic, two-step approach. A simulation study and revisiting Bandiera et al. (2020)'s study of executive time use demonstrate these results. The approach accommodates thousands of parameters and doesn't require custom algorithms specific to each model, making it accessible for applied researchers
Deep neural networks have been shown to provide accurate function approximations in high dimensions. However, fitting network parameters requires informative training data that are often challenging to collect in science and engineering applications. This work proposes Neural Galerkin schemes based on deep learning that generate training data with active learning for numerically solving high-dimensional partial differential equations. Neural Galerkin schemes build on the Dirac-Frenkel variational principle to train networks by minimizing the residual sequentially over time, which enables adaptively collecting new training data in a self-informed manner that is guided by the dynamics described by the partial differential equations. This is in contrast to other machine learning methods that aim to fit network parameters globally in time without taking into account training data acquisition. Our finding is that the active form of gathering training data of the proposed Neural Galerkin schemes is key for numerically realizing the expressive power of networks in high dimensions. Numerical experiments demonstrate that Neural Galerkin schemes have the potential to enable simulating phenomena and processes with many variables for which traditional and other deep-learning-based solvers fail, especially when features of the solutions evolve locally such as in high-dimensional wave propagation problems and interacting particle systems described by Fokker-Planck and kinetic equations.
Deep reinforcement learning algorithms can perform poorly in real-world tasks due to the discrepancy between source and target environments. This discrepancy is commonly viewed as the disturbance in transition dynamics. Many existing algorithms learn robust policies by modeling the disturbance and applying it to source environments during training, which usually requires prior knowledge about the disturbance and control of simulators. However, these algorithms can fail in scenarios where the disturbance from target environments is unknown or is intractable to model in simulators. To tackle this problem, we propose a novel model-free actor-critic algorithm -- namely, state-conservative policy optimization (SCPO) -- to learn robust policies without modeling the disturbance in advance. Specifically, SCPO reduces the disturbance in transition dynamics to that in state space and then approximates it by a simple gradient-based regularizer. The appealing features of SCPO include that it is simple to implement and does not require additional knowledge about the disturbance or specially designed simulators. Experiments in several robot control tasks demonstrate that SCPO learns robust policies against the disturbance in transition dynamics.
Object detection typically assumes that training and test data are drawn from an identical distribution, which, however, does not always hold in practice. Such a distribution mismatch will lead to a significant performance drop. In this work, we aim to improve the cross-domain robustness of object detection. We tackle the domain shift on two levels: 1) the image-level shift, such as image style, illumination, etc, and 2) the instance-level shift, such as object appearance, size, etc. We build our approach based on the recent state-of-the-art Faster R-CNN model, and design two domain adaptation components, on image level and instance level, to reduce the domain discrepancy. The two domain adaptation components are based on H-divergence theory, and are implemented by learning a domain classifier in adversarial training manner. The domain classifiers on different levels are further reinforced with a consistency regularization to learn a domain-invariant region proposal network (RPN) in the Faster R-CNN model. We evaluate our newly proposed approach using multiple datasets including Cityscapes, KITTI, SIM10K, etc. The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.
Detecting carried objects is one of the requirements for developing systems to reason about activities involving people and objects. We present an approach to detect carried objects from a single video frame with a novel method that incorporates features from multiple scales. Initially, a foreground mask in a video frame is segmented into multi-scale superpixels. Then the human-like regions in the segmented area are identified by matching a set of extracted features from superpixels against learned features in a codebook. A carried object probability map is generated using the complement of the matching probabilities of superpixels to human-like regions and background information. A group of superpixels with high carried object probability and strong edge support is then merged to obtain the shape of the carried object. We applied our method to two challenging datasets, and results show that our method is competitive with or better than the state-of-the-art.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191