Maximising the detection of intrusions is a fundamental and often critical aim of perimeter surveillance. Commonly, this requires a decision-maker to optimally allocate multiple searchers to segments of the perimeter. We consider a scenario where the decision-maker may sequentially update the searchers' allocation, learning from the observed data to improve decisions over time. In this work we propose a formal model and solution methods for this sequential perimeter surveillance problem. Our model is a combinatorial multi-armed bandit (CMAB) with Poisson rewards and a novel filtered feedback mechanism - arising from the failure to detect certain intrusions. Our solution method is an upper confidence bound approach and we derive upper and lower bounds on its expected performance. We prove that the gap between these bounds is of constant order, and demonstrate empirically that our approach is more reliable in simulated problems than competing algorithms.

Fair machine learning is receiving an increasing attention in machine learning fields. Researchers in fair learning have developed correlation or association-based measures such as demographic disparity, mistreatment disparity, calibration, causal-based measures such as total effect, direct and indirect discrimination, and counterfactual fairness, and fairness notions such as equality of opportunity and equal odds that consider both decisions in the training data and decisions made by predictive models. In this paper, we develop a new causal-based fairness notation, called equality of effort. Different from existing fairness notions which mainly focus on discovering the disparity of decisions between two groups of individuals, the proposed equality of effort notation helps answer questions like to what extend a legitimate variable should change to make a particular individual achieve a certain outcome level and addresses the concerns whether the efforts made to achieve the same outcome level for individuals from the protected group and that from the unprotected group are different. We develop algorithms for determining whether an individual or a group of individuals is discriminated in terms of equality of effort. We also develop an optimization-based method for removing discriminatory effects from the data if discrimination is detected. We conduct empirical evaluations to compare the equality of effort and existing fairness notion and show the effectiveness of our proposed algorithms. Introduction Fair machine learning is receiving an increasing attention in machine learning fields. Discrimination is unfair treatment towards individuals based on the group to which they are perceived to belong. The first endeavor of the research community to achieve fairness is developing correlation or association-based measures, including demographic disparity (e.g., risk difference), mistreatment disparity, calibration, etc. (Romei and Ruggieri 2014; Luong, Ruggieri, and Turini 2011; ˇ Zliobaite, Kamiran, and Calders 2011; Dwork et al. 2012; Feldman et al. 2015), which mainly focus on discovering the disparity of certain statistical metrics between two groups of individuals. However, as paid increasing attention recently (Zhang, Wu, and Wu 2017b; Kilbertus et al. 2017; Nabi and Shpitser 2018), unlawful discrimination is a causal connection between the challenged decision and a protected characteristic, which cannot be captured by simple correlation or association concepts.

Despite impressive performance on numerous visual tasks, Convolutional Neural Networks (CNNs) --- unlike brains --- are often highly sensitive to small perturbations of their input, e.g. adversarial noise leading to erroneous decisions. We propose to regularize CNNs using large-scale neuroscience data to learn more robust neural features in terms of representational similarity. We presented natural images to mice and measured the responses of thousands of neurons from cortical visual areas. Next, we denoised the notoriously variable neural activity using strong predictive models trained on this large corpus of responses from the mouse visual system, and calculated the representational similarity for millions of pairs of images from the model's predictions. We then used the neural representation similarity to regularize CNNs trained on image classification by penalizing intermediate representations that deviated from neural ones. This preserved performance of baseline models when classifying images under standard benchmarks, while maintaining substantially higher performance compared to baseline or control models when classifying noisy images. Moreover, the models regularized with cortical representations also improved model robustness in terms of adversarial attacks. This demonstrates that regularizing with neural data can be an effective tool to create an inductive bias towards more robust inference.

The determination of the computational complexity of multi-agent pathfinding on directed graphs has been an open problem for many years. For undirected graphs, solvability can be decided in polynomial time, as has been shown already in the eighties. Further, recently it has been shown that a special case on directed graphs is solvable in polynomial time. In this paper, we show that the problem is NP-hard in the general case. In addition, some upper bounds are proven.

November 13, 2019 Abstract Collision avoidance is one of the most primary problems in the decentralized multiagent navigation: while the agents are moving towards their own targets, attentions should be paid to avoid the collisions with the others. In this paper, we introduced the concept of the local action cell, which provides for each agent a set of velocities that are safe to perform. Consequently, as long as the local action cells are updated on time and each agent selects its motion within the corresponding cell, there should be no collision caused. Furthermore, we coupled the local action cell with an adaptive learning framework, in which the performance of selected motions are evaluated and used as the references for making decisions in the following updates. The efficiency of the proposed approaches were demonstrated through the experiments for three commonly considered scenarios, where the comparisons have been made with several well studied strategies. 1 Introduction Collision-free navigation is a fundamental and important problem in the design of the multiagent systems, which are widely applied in the fields such as robots control and traffic engineering.

-- T o solve multi-step manipulation tasks in the real world, an autonomous robot must take actions to observe its environment and react to unexpected observations. This may require opening a drawer to observe its contents or moving an object out of the way to examine the space behind it. If the robot fails to detect an important object, it must update its belief about the world and compute a new plan of action. Additionally, a robot that acts noisily will never exactly arrive at a desired state. Still, it is important that the robot adjusts accordingly in order to keep making progress towards achieving the goal. In this work, we present an online planning and execution system for robots faced with these kinds of challenges. Our approach is able to efficiently solve partially observable problems both in simulation and in a real-world kitchen. Robots acting autonomously in human environments are faced with a variety of challenges. First, they must make both discrete decisions about what object to manipulate as well as continuous decisions about which motions to execute to achieve a desired interaction. Planning in these large hybrid spaces is the subject of integrated T ask and Motion Planning (T AMP) [1], [2], [3], [4], [5], [6].

Answering complex questions involving multiple entities and relations is a challenging task. Logically, the answer to a complex question should be derived by decomposing the complex question into multiple simple sub-questions and then answering those sub-questions. Existing work has followed this strategy but has not attempted to optimize the order how those sub-questions are answered. As a result, the sub-questions are answered in an arbitrary order, leading to larger search space and higher risk of missing an answer. In this paper, we propose a novel reinforcement learning (RL) approach to answering complex questions that can learn a policy to dynamically decide which sub-question should be answered at each state of reasoning. We leverage the expected value-variance criterion to enable the learned policy to balance between the risk and utility of answering a sub-question. Experiment results show that the RL approach can substantially improve the optimal-ity of ordering the sub-questions, leading to improved accuracy of question answering. The proposed method for learning to order sub-questions is general and can thus be potentially combined with many existing ideas for answering complex questions to enhance their performance. Introduction Real-world questions can be complex, involving multiple interrelated entities and relations, which we refer to as complex questions . For example, "who writes Harry Potter" is a simple question that only involves a single entity and a relation, while "Which city is the filming location of the book written by J.K.Rowling and held Olympics?" is a complex question, which consists of multiple entities and relations. How to automatically answer such complex questions is a significant scientific challenge because it requires a system to capture the dependencies between different components of the questions and reason over them. Recently, some recent work has attempted to tackle such complex questions (Talmor and Berant 2018; Iyyer, Yih, and Chang 2016; Min et al. 2019; Zhang et al. 2019), usually by decomposing a complex question into a sequence of simple questions and answering them based on a computation tree derived from the original question that can capture the dependency between sub-questions as shown in Figure 1.

Standardization of solver input languages has been a main dr iver for the growth of several areas within knowledge representation and reasoning, fostering the exploitation in actual applications. In this document we present the ASP-Core-2 standard input language for Answer Set Programming, which h as been adopted in ASP Competition events since 2013. KEYWORDS: Answer Set Programming, Standard Language, Knowledge Rep resentation and Reasoning, Standardization 2 Calimeri et al. 1 Introduction The process of standardizing the input languages of solvers for knowledge representation and reasoning research areas has been of utmost importance for the growth o f the related research communities: this has been the case for, e.g., the CNF-DIMACS format for SA T, th en extended to describe input formats for Max-SA T and QBF problems, the OPB format for pseudo-Boolean problems, somehow at the intersection between the CNF-DIMACS format and the LP format for Integer L inear Programming, the XCSP3 format for CP solving, SMT -LIB format for SMT solving, and the STRIP S/ PDDL language for automatic planning. The availability of such common input languages have l ed to the development of e ffi cient solvers in di ff erent KR communities, through a series of solver competitio ns that have pushed the adoption of these standards. The availability of e ffi cient solvers, together with a presence of a common interfac e language, has helped the exploitation of these methodologies in appli cations. The same has happened for Answer Set Programming (ASP) (Brew ka et al. 2011), a well-known approach to knowledge representation and reasoning with root s in the areas of logic programming and nonmonotonic reasoning (Gelfond and Lifschitz 1991), through the development of the ASP-Core language (Calimeri et al. 2011). The first ASP-Core version was a rule-based language whose syntax stems from plain Datalog and Prolog, and was a conservative extension t o the non-ground case of the Core language adopted in the First ASP Competition held in 2002 during the D agstuhl Seminar "Nonmonotonic Reasoning, Answer Set Programming and Constraints"

For some problems, humans may not be able to accurately judge the goodness of AIproposed solutions. Irving, Christiano, and Amodei (2018) propose that in such cases, we may use a debate between two AI systems to amplify the problem-solving capabilities of a human judge. We introduce a mathematical framework that can model debates of this type and propose that the quality of debate designs should be measured by the accuracy of the most persuasive answer. We describe a simple instance of the debate framework called feature debate and analyze the degree to which such debates track the truth. We argue that despite being ver y simple, feature debates nonetheless capture many aspects o f practical debates such as the incentives to confuse the judg e or stall to prevent losing. We then outline how these models should be generalized to analyze a wider range of debate phenomena.

Keep it Consistent: T opic-A ware Storytelling from an Image Stream via Iterative Multi-agent Communication Ruize Wang 1, Zhongyu Wei 2, Piji Li 3, Haijun Shan 4, Ji Zhang 4, Qi Zhang 5, Xuanjing Huang 5 1 Academy for Engineering and Technology, Fudan University, China 2 School of Data Science, Fudan University, China 3 Tencent AI Lab, China 4 Zhejiang Lab, China 5 School of Computer Science, Fudan University, China { rzwang18,zywei,qz,xjhuang} @fudan.edu.cn; Abstract Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically. Existing approaches construct text description independently for each image and roughly concatenate them as a story, which leads to the problem of generating semantically incoherent content. In this paper, we proposed a new way for visual storytelling by introducing a topic description task to detect the global semantic context of an image stream. A story is then constructed with the guidance of the topic description. In order to combine the two generation tasks, we propose a multi-agent communication framework that regards the topic description generator and the story generator as two agents and learn them simultaneously via iterative updating mechanism. We validate our approach on VIST, where quantitative results, ablations, and human evaluation demonstrate our method's good ability in generating stories with higher quality compared to state-of-the-art methods. 1 Introduction Image-to-text generation is an important topic in artificial intelligence (AI) which connects computer vision (CV) and natural language processing (NLP). Popular tasks include image captioning (Karpathy and Fei-Fei 2015; Ren et al. 2017; Vinyals et al. 2017) and question answering (Antol et al. 2015; Y u et al. 2017; Fan et al. 2018a; Fan et al. 2018b), aiming at generating a short sentence or a phrase conditioned on certain visual information. It requires the model to understand the main idea of the image stream and generate coherent sentences. Most of existing methods (Huang et al. 2016; Liu et al. 2017; Y u, Bansal, and Berg 2017; Wang et al. 2018a) for visual storytelling extend approaches of image captioning without considering topic information of the image sequence, which causes the problem of generating semantically incoherent content.