论文检索

Fahmid Morshed Fahid, Jonathan Rowe, Yeojin Kim, Shashank Srivastava, James Lester

Pedagogical planners can provide adaptive support to students in narrative-centered learning environments by dynamically scaffolding student learning and tailoring problem scenarios. Reinforcement learning (RL) is frequently used for pedagogical planning in narrative-centered learning environments. However, RL-based pedagogical planning raises significant challenges due to the scarcity of data for training RL policies. Most prior work has relied on limited-size datasets and offline RL techniques for policy learning. Unfortunately, offline RL techniques do not support on-demand exploration and evaluation, which can adversely impact the quality of induced policies. To address the limitation of data scarcity and offline RL, we propose INSIGHT, an online RL framework for training data-driven pedagogical policies that optimize student learning in narrative-centered learning environments. The INSIGHT framework consists of three components: a narrative-centered learning environment simulator, a simulated student agent, and an RL-based pedagogical planner agent, which uses a reward metric that is associated with effective student learning processes. The framework enables the generation of synthetic data for on-demand exploration and evaluation of RL-based pedagogical planning. We have implemented INSIGHT with OpenAI Gym for a narrative-centered learning environment testbed with rule-based simulated student agents and a deep Q-learning-based pedagogical planner. Our results show that online deep RL algorithms can induce near-optimal pedagogical policies in the INSIGHT framework, while offline deep RL algorithms only find suboptimal policies even with large amounts of data.

Anisha Gupta, Seung Lee, Bradford Mott, Srijita Chakraburty, Krista Glazewski, Anne Ottenbreit-Leftwich, Adam Scribner, Cindy E. Hmelo-Silver, James Lester

Artificial intelligence (AI) is quickly finding broad application in every sector of society. This rapid expansion of AI has increased the need to cultivate an AI-literate workforce, and it calls for introducing AI education into K-12 classrooms to foster students’ awareness and interest in AI. With rich narratives and opportunities for situated problem solving, story-driven game-based learning offers a promising approach for creating engaging and effective K-12 AI learning experiences. In this paper, we present our ongoing work to iteratively design, develop, and evaluate a story-driven game-based learning environment focused on AI education for upper elementary students (ages 8 to 11). The game features a science inquiry problem centering on an endangered species and incorporates a Use-Modify-Create scaffolding framework to promote student learning. We present findings from an analysis of data collected from 16 students playing the game's quest focused on AI planning. Results suggest that the scaffolding framework provided students with the knowledge they needed to advance through the quest and that overall, students experienced positive learning outcomes.

Zakaria Mehrab, Logan Stundal, Srinivasan Venkatramanan, Samarth Swarup, Bryan Leroy Lewis, Henning S. Mortveit, Christopher L. Barrett, Abhishek Pandey, Chad R. Wells, Alison P. Galvani 等

Large-scale population displacements arising from conflict-induced forced migration generate uncertainty and introduce several policy challenges. Addressing these concerns requires an interdisciplinary approach that integrates knowledge from both computational modeling and social sciences. We propose a generalized computational agent-based modeling framework grounded by Theory of Planned Behavior to model conflict-induced migration outflows within Ukraine during the start of that conflict in 2022. Existing migration modeling frameworks that attempt to address policy implications primarily focus on destination while leaving absent a generalized computational framework grounded by social theory focused on the conflict-induced region. We propose an agent-based framework utilizing a spatiotemporal gravity model and a Bi-threshold model over a Graph Dynamical System to update migration status of agents in conflict-induced regions at fine temporal and spatial granularity. This approach significantly outperforms previous work when examining the case of Russian invasion in Ukraine. Policy implications of the proposed framework are demonstrated by modeling the migration behavior of Ukrainian civilians attempting to flee from regions encircled by Russian forces. We also showcase the generalizability of the model by simulating a past conflict in Burundi, an alternative conflict setting. Results demonstrate the utility of the framework for assessing conflict-induced migration in varied settings as well as identifying vulnerable civilian populations.

Hao Sun, Xiaoli Tang, Chengyi Yang, Zhenpeng Yu, Xiuli Wang, Qijie Ding, Zengxiang Li, Han Yu

Gas usage estimation plays a critical role in various aspects of the power generation and delivery business, including budgeting, resource planning, and environmental preservation. Federated Learning (FL) has demonstrated its potential in enhancing the accuracy and reliability of gas usage estimation by enabling distributedly owned data to be leveraged, while ensuring privacy and confidentiality. However, to effectively motivate stakeholders to contribute their high-quality local data and computational resources for this purpose, incentive mechanism design is key. In this paper, we report our experience designing and deploying the Hierarchical FL Incentive mechanism for Gas usage estimation (HiFi-Gas) system. It is designed to cater to the unique structure of gas companies and their affiliated heating stations. HiFi-Gas provides effective incentivization in a hierarchical federated learning framework that consists of a horizontal federated learning (HFL) component for effective collaboration among gas companies and multiple vertical federated learning (VFL) components for the gas company and its affiliated heating stations. To motivate active participation and ensure fairness among gas companies and heating stations, we incorporate a multi-dimensional contribution-aware reward distribution function that considers both data quality and model contributions. Since its deployment in the ENN Group in December 2022, HiFi-Gas has successfully provided incentives for gas companies and heating stations to actively participate in FL training, resulting in more than 12% higher average gas usage estimation accuracy and substantial gas procurement cost savings. This implementation marks the first successful deployment of a hierarchical FL incentive approach in the energy industry.

Richard S. Sutton, Marlos C. Machado, G. Zacharias Holland, David Szepesvari, Finbarr Timbers, Brian Tanner, Adam White

To achieve the ambitious goals of artificial intelligence, reinforcement learning must include planning with a model of the world that is abstract in state and time. Deep learning has made progress with state abstraction, but temporal abstraction has rarely been used, despite extensively developed theory based on the options framework. One reason for this is that the space of possible options is immense, and the methods previously proposed for option discovery do not take into account how the option models will be used in planning. Options are typically discovered by posing subsidiary tasks, such as reaching a bottleneck state or maximizing the cumulative sum of a sensory signal other than reward. Each subtask is solved to produce an option, and then a model of the option is learned and made available to the planning process. In most previous work, the subtasks ignore the reward on the original problem, whereas we propose subtasks that use the original reward plus a bonus based on a feature of the state at the time the option terminates. We show that option models obtained from such reward-respecting subtasks are much more likely to be useful in planning than eigenoptions, shortest path options based on bottleneck states, or reward-respecting options generated by the option-critic. Reward respecting subtasks strongly constrain the space of options and thereby also provide a partial solution to the problem of option discovery. Finally, we show how values, policies, options, and models can all be learned online and off-policy using standard algorithms and general value functions.

Gregor Behnke

Planning is the act of deliberative thinking before acting. It is based on a symbolic model of the world and the options to act in it, usually defined in function-free first-order logic. The task is to find a sequence of actions (a plan) that leads from a given current state to a desired goal state. The basic, purely physical description may be augmented with a partially ordered grammar-like structure (a Hierarchical Task Network or HTN), which can describe expert knowledge, or practical, legal, or operational requirements. In this talk, I will survey a variety of methods for automatically deriving plans using symbolic methods for planning -- from both my past and future research. These symbolic methods -- in some sense -- translate planning problems into other, simpler symbolic representations and reason over them to find plans. As a basis for these methods, I will firstly introduce relevant theoretical results on planning. First, I will discuss the expressive power of planning formalisms (ECAI'14, ICAPS'16) and second, the computational complexity of HTN planning and related tasks such as HTN plan verification, plan modification, and plan recognition (ICAPS'15, ICAPS'16). Based on these theoretical results, I will develop why SAT-based HTN planning is possible and how it can be implemented. To this end, I will survey several of my publications at top-tier conferences, including papers at ICAPS'17, AAAI'18, AAAI'19, IJCAI'19, AAAI'20, and ICAPS'21 -- in which I developed an highly SAT-based planner for HTN problems including the ability to find optimal plans as well as the grounding as a preprocessing step. Here I will also give an outlook on future developments and new ideas that I propose for SAT-based planning -- including the exploitation of structures in plan (e.g.\ landmarks or operator-counting constraints). Next, I will present the idea of expressing lifted classical planning as SAT (ICAPS'22). The resulting planner LiSAT was the first lifted SAT-based planner -- and proved highly efficient and outperformed all other lifted planners at the time of publication. Notably, LiSAT was the first planner (lifted or grounded) and still is the only one to solve the challenging OrganicSynthesis benchmark -- and could even prove optimality for all plans. I will also outline future ideas to further improve the efficiency of LiSAT. Lastly, I introduce the notion of planning with symbolic symbolic representations (AAAI'21 and ICAPS'23). Here one uses Binary Decision Diagrams to encode large sets of states efficiently. For expressing the additional structure encoded by HTNs, I show how BDDs can be suitably integrated into finite automata. Based on this representation, an efficient and optimal planning algorithm can be derived. Additionally, I show how this algorithm can be extended to also cover oversubscription planning.

Mohammad Abdulaziz

Interactive theorem provers (ITPs) are computer programs in which axioms and a conjecture are stated in a formal language, and a user provides the ITP with relatively high-level steps of a formal proof for the conjecture. Then, by invoking automated theorem provers, the ITP tries to generate low-level steps that fill the gaps between the steps provided by the user, thus forming a complete formal proof of the conjecture. The ITP also checks the entire formal proof against the axioms, thus confirming the soundness of all derivations in the formal proof. In this talk, I will discuss the existing opportunities and potential benefits to applying ITPs to reason about and verify AI concepts, algorithms, and software. I will also discuss the challenges we have to being able to apply ITPs in AI and reap those benefits. I will do so by discussing a number of my previous projects on the application of ITPs to different AI concepts, algorithms, and software systems. These projects span different areas of planning (classical planning, temporal planning, and planning under uncertainty) as well as algorithms with applications in algorithmic game theory, like general graph matching and online matching.

Yuyao Zhang, Ke Guo, Xiao Zhou

Artificial light plays an integral role in modern cities, significantly enhancing human productivity and the efficiency of civilization. However, excessive illumination can lead to light pollution, posing non-negligible threats to economic burdens, ecosystems, and human health. Despite its critical importance, the exploration of its causes remains relatively limited within the field of artificial intelligence, leaving an incomplete understanding of the factors contributing to light pollution and sustainable illumination planning distant. To address this gap, we introduce a novel framework named Causally Aware Generative Adversarial Networks (CAGAN). This innovative approach aims to uncover the fundamental drivers of light pollution within cities and offer intelligent solutions for optimal illumination resource allocation in the context of sustainable urban development. We commence by examining light pollution across 33,593 residential areas in seven global metropolises. Our findings reveal substantial influences on light pollution levels from various building types, notably grasslands, commercial centers and residential buildings as significant contributors. These discovered causal relationships are seamlessly integrated into the generative modeling framework, guiding the process of generating light pollution maps for diverse residential areas. Extensive experiments showcase CAGAN’s potential to inform and guide the implementation of effective strategies to mitigate light pollution. Our code and data are publicly available at https://github.com/zhangyuuao/Light_Pollution_CAGAN.

Gustavo Perez, Subhransu Maji, Daniel Sheldon

Many applications use computer vision to detect and count objects in massive image collections. However, automated methods may fail to deliver accurate counts, especially when the task is very difficult or requires a fast response time. For example, during disaster response, aid organizations aim to quickly count damaged buildings in satellite images to plan relief missions, but pre-trained building and damage detectors often perform poorly due to domain shifts. In such cases, there is a need for human-in-the-loop approaches to accurately count with minimal human effort. We propose DISCount -- a detector-based importance sampling framework for counting in large image collections. DISCount uses an imperfect detector and human screening to estimate low-variance unbiased counts. We propose techniques for counting over multiple spatial or temporal regions using a small amount of screening and estimate confidence intervals. This enables end-users to stop screening when estimates are sufficiently accurate, which is often the goal in real-world applications. We demonstrate our method with two applications: counting birds in radar imagery to understand responses to climate change, and counting damaged buildings in satellite imagery for damage assessment in regions struck by a natural disaster. On the technical side we develop variance reduction techniques based on control variates and prove the (conditional) unbiasedness of the estimators. DISCount leads to a 9-12x reduction in the labeling costs to obtain the same error rates compared to naive screening for tasks we consider, and surpasses alternative covariate-based screening approaches.

Bo Lin, Shoshanna Saxe, Timothy C. Y. Chan

Cycling stress assessment, which quantifies cyclists' perceived stress imposed by the built environment and motor traffics, increasingly informs cycling infrastructure planning and cycling route recommendation. However, currently calculating cycling stress is slow and data-intensive, which hinders its broader application. In this paper, We propose a deep learning framework to support accurate, fast, and large-scale cycling stress assessments for urban road networks based on street-view images. Our framework features i) a contrastive learning approach that leverages the ordinal relationship among cycling stress labels, and ii) a post-processing technique that enforces spatial smoothness into our predictions. On a dataset of 39,153 road segments collected in Toronto, Canada, our results demonstrate the effectiveness of our deep learning framework and the value of using image data for cycling stress assessment in the absence of high-quality road geometry and motor traffic data.

Jordi Laguarta Soler, Thomas Friedel, Sherrie Wang

Accurate crop type maps are an essential source of information for monitoring yield progress at scale, projecting global crop production, and planning effective policies. To date, however, crop type maps remain challenging to create in low- and middle-income countries due to a lack of ground truth labels for training machine learning models. Field surveys are the gold standard in terms of accuracy but require an often-prohibitively large amount of time, money, and statistical capacity. In recent years, street-level imagery, such as Google Street View, KartaView, and Mapillary, has become available around the world. Such imagery contains rich information about crop types grown at particular locations and times. In this work, we develop an automated system to generate crop type ground references using deep learning and Google Street View imagery. The method efficiently curates a set of street-view images containing crop fields, trains a model to predict crop types using either weakly-labeled images from disparate out-of-domain sources or zero-shot labeled street view images with GPT-4V, and combines the predicted labels with remote sensing time series to create a wall-to-wall crop type map. We show that, in Thailand, the resulting country-wide map of rice, cassava, maize, and sugarcane achieves an accuracy of 93%. We publicly release the first-ever crop type map for all of Thailand 2022 at 10m-resolution with no gaps. To our knowledge, this is the first time a 10m-resolution, multi-crop map has been created for any smallholder country. As the availability of roadside imagery expands, our pipeline provides a way to map crop types at scale around the globe, especially in underserved smallholder regions.

Tianyuan Huang, Zejia Wu, Jiajun Wu, Jackelyn Hwang, Ram Rajagopal

Urban transformations have profound societal impact on both individuals and communities at large. Accurately assessing these shifts is essential for understanding their underlying causes and ensuring sustainable urban planning. Traditional measurements often encounter constraints in spatial and temporal granularity, failing to capture real-time physical changes. While street view imagery, capturing the heartbeat of urban spaces in a pedestrian point of view, can add as a high-definition, up-to-date, and on-the-ground visual proxy of urban change. We curate the largest street view time series dataset to date, and propose an end-to-end change detection model to effectively capture physical alterations in the built environment at scale. We demonstrate the effectiveness of our proposed method by benchmark comparisons with previous literature and implementing it at the city-wide level. Our approach has the potential to supplement existing dataset and serve as a fine-grained and accurate assessment of urban change.

Marc Grimson, Rafael Almeida, Qinru Shi, Yiwei Bai, Héctor Angarita, Felipe Siqueira Pacheco, Rafael Schmitt, Alexander Flecker, Carla P. Gomes

Sustainability challenges inherently involve the consideration of multiple competing objectives. The Pareto frontier – the set of all optimal solutions that cannot be improved with respect to one objective without negatively affecting another – is a crucial decision-making tool for navigating sustainability challenges as it highlights the inherent trade-offs among conflicting objectives. Our research is motivated by the strategic planning of hydropower in the Amazon basin, one of the earth’s largest and most biodiverse river systems, where the need to increase energy production coincides with the pressing requirement of minimizing detrimental environmental impacts. We investigate an innovative strategy that pairs hydropower with Floating Photovoltaic Solar Panels (FPV). We provide a new extended multi-tree network formulation, which enables the consideration of multiple dam configurations. To address the computational challenge of scaling up the Pareto optimization framework to tackle multiple objectives across the entire Amazon basin, we further enhance the state-of-the-art algorithm for Pareto frontiers in tree-structured networks with two improvements. We introduce affine transformations induced by the sub-frontiers to compute Pareto dominance and provide strategies for merging sub-trees, significantly increasing the pruning of dominated solutions. Our experiments demonstrate considerable speedups, in some cases by more than an order of magnitude, while maintaining optimality guarantees, thus allowing us to more effectively approximate the Pareto frontiers. Moreover, our findings suggest significant shifts towards higher energy values in the Pareto frontier when pairing hybrid hydropower with FPV solutions, potentially amplifying energy production while mitigating adverse impacts.

Inaam Ashraf, Janine Strotherm, Luca Hermes, Barbara Hammer

Water distribution systems (WDS) are an integral part of critical infrastructure which is pivotal to urban development. As 70% of the world's population will likely live in urban environments in 2050, efficient simulation and planning tools for WDS play a crucial role in reaching UN's sustainable developmental goal (SDG) 6 - "Clean water and sanitation for all". In this realm, we propose a novel and efficient machine learning emulator, more precisely, a physics-informed deep learning (DL) model, for hydraulic state estimation in WDS. Using a recursive approach, our model only needs a few graph convolutional neural network (GCN) layers and employs an innovative algorithm based on message passing. Unlike conventional machine learning tasks, the model uses hydraulic principles to infer two additional hydraulic state features in the process of reconstructing the available ground truth feature in an unsupervised manner. To the best of our knowledge, this is the first DL approach to emulate the popular hydraulic simulator EPANET, utilizing no additional information. Like most DL models and unlike the hydraulic simulator, our model demonstrates vastly faster emulation times that do not increase drastically with the size of the WDS. Moreover, we achieve high accuracy on the ground truth and very similar results compared to the hydraulic simulator as demonstrated through experiments on five real-world WDS datasets.

Matthew Cleaveland, Insup Lee, George J. Pappas, Lars Lindemann

Conformal prediction is a statistical tool for producing prediction regions of machine learning models that are valid with high probability. However, applying conformal prediction to time series data leads to conservative prediction regions. In fact, to obtain prediction regions over T time steps with confidence 1--delta, previous works require that each individual prediction region is valid with confidence 1--delta/T. We propose an optimization-based method for reducing this conservatism to enable long horizon planning and verification when using learning-enabled time series predictors. Instead of considering prediction errors individually at each time step, we consider a parameterized prediction error over multiple time steps. By optimizing the parameters over an additional dataset, we find prediction regions that are not conservative. We show that this problem can be cast as a mixed integer linear complementarity program (MILCP), which we then relax into a linear complementarity program (LCP). Additionally, we prove that the relaxed LP has the same optimal cost as the original MILCP. Finally, we demonstrate the efficacy of our method on case studies using pedestrian trajectory predictors and F16 fighter jet altitude predictors.

Chengtai Cao, Xinhong Chen, Jianping Wang, Qun Song, Rui Tan, Yung-Hui Li

Autonomous driving systems rely on precise trajectory prediction for safe and efficient motion planning. Despite considerable efforts to enhance prediction accuracy, inherent uncertainties persist due to data noise and incomplete observations. Many strategies entail formalizing prediction outcomes into distributions and utilizing variance to represent uncertainty. However, our experimental investigation reveals that existing trajectory prediction models yield unreliable uncertainty estimates, necessitating additional customized calibration processes. On the other hand, directly applying current calibration techniques to prediction outputs may yield sub-optimal results due to using a universal scaler for all predictions and neglecting informative data cues. In this paper, we propose Customized Calibration Temperature with Regularizer (CCTR), a generic framework that calibrates the output distribution. Specifically, CCTR 1) employs a calibration-based regularizer to align output variance with the discrepancy between prediction and ground truth and 2) generates a tailor-made temperature scaler for each prediction using a post-processing network guided by context and historical information. Extensive evaluation involving multiple prediction and planning methods demonstrates the superiority of CCTR over existing calibration algorithms and uncertainty-aware methods, with significant improvements of 11%-22% in calibration quality and 17%-46% in motion planning.

Xiaoyang Xu, Hu Ding

Optimal transport is a fundamental topic that has attracted a great amount of attention from the optimization community in the past decades. In this paper, we consider an interesting discrete dynamic optimal transport problem: can we efficiently update the optimal transport plan when the weights or the locations of the data points change? This problem is naturally motivated by several applications in machine learning. For example, we often need to compute the optimal transport cost between two different data sets; if some changes happen to a few data points, should we re-compute the high complexity cost function or update the cost by some efficient dynamic data structure? We are aware that several dynamic maximum flow algorithms have been proposed before, however, the research on dynamic minimum cost flow problem is still quite limited, to the best of our knowledge. We propose a novel 2D Skip Orthogonal List together with some dynamic tree techniques. Although our algorithm is based on the conventional simplex method, it can efficiently find the variable to pivot within expected O(1) time, and complete each pivoting operation within expected O(|V|) time where V is the set of all supply and demand nodes. Since dynamic modifications typically do not introduce significant changes, our algorithm requires only a few simplex iterations in practice. So our algorithm is more efficient than re-computing the optimal transport cost that needs at least one traversal over all |E|=O(|V|^2) variables, where |E| denotes the number of edges in the network. Our experiments demonstrate that our algorithm significantly outperforms existing algorithms in the dynamic scenarios.

Mingyu Guo, Jialiang Li, Aneta Neumann, Frank Neumann, Hung Nguyen

We propose a combinatorial optimisation model called Limited Query Graph Connectivity Test. We consider a graph whose edges have two possible states (On/Off). The edges' states are hidden initially. We could query an edge to reveal its state. Given a source s and a destination t, we aim to test s−t connectivity by identifying either a path (consisting of only On edges) or a cut (consisting of only Off edges). We are limited to B queries, after which we stop regardless of whether graph connectivity is established. We aim to design a query policy that minimizes the expected number of queries. Our model is mainly motivated by a cyber security use case where we need to establish whether attack paths exist in a given network, between a source (i.e., a compromised user node) and a destination (i.e., a high-privilege admin node). Edge query is resolved by manual effort from the IT admin, which is the motivation behind query minimization. Our model is highly related to Stochastic Boolean Function Evaluation (SBFE). There are two existing exact algorithms for SBFE that are prohibitively expensive. We propose a signifcantly more scalable exact algorithm. While previous exact algorithms only scale for trivial graphs (i.e., past works experimented on at most 20 edges), we empirically demonstrate that our algorithm is scalable for a wide range of much larger practical graphs (i.e., graphs representing Windows domain networks with tens of thousands of edges). We also propose three heuristics. Our best-performing heuristic is via limiting the planning horizon of the exact algorithm. The other two are via reinforcement learning (RL) and Monte Carlo tree search (MCTS). We also derive an algorithm for computing the performance lower bound. Experimentally, we show that all our heuristics are near optimal. The heuristic building on the exact algorithm outperforms all other heuristics, surpassing RL, MCTS and eight existing heuristics ported from SBFE and related literature.

Simon Dold, Malte Helmert

Classical planning considers a given task and searches for a plan to solve it. Some tasks are harder to solve than others. We can measure the 'hardness' of a task with the novelty width and the correlation complexity. In this work, we compare these measures. Additionally, we introduce the river measure, a new measure that is based on potential heuristics and therefore similar to the correlation complexity but also comparable to the novelty width. We show that the river measure is upper bounded by the correlation complexity and by the novelty width +1. Furthermore, we show that we can convert a planning task with a polynomial blowup of the task size to ensure that a heuristic of dimension 2 exists that gives rise to backtrack-free search.

Zhe Chen, Daniel Harabor, Jiaoyang Li, Peter J. Stuckey

Multi-Agent Path Finding (MAPF) is a fundamental problem in robotics that asks us to compute collision-free paths for a team of agents, all moving across a shared map. Although many works appear on this topic, all current algorithms struggle as the number of agents grows. The principal reason is that existing approaches typically plan free-flow optimal paths, which creates congestion. To tackle this issue, we propose a new approach for MAPF where agents are guided to their destination by following congestion-avoiding paths. We evaluate the idea in two large-scale settings: one-shot MAPF, where each agent has a single destination, and lifelong MAPF, where agents are continuously assigned new destinations. Empirically, we report large improvements in solution quality for one-short MAPF and in overall throughput for lifelong MAPF.