Inspired by insects' visual brains, this paper presents original modelling of a complementary visual neuronal systems model for real-time and robust collision sensing. Two categories of wide-field motion sensitive neurons, i.e., the lobula giant movement detectors (LGMDs) in locusts and the lobula plate tangential cells (LPTCs) in flies, have been studied, intensively. The LGMDs have specific selectivity to approaching objects in depth that threaten collision; whilst the LPTCs are only sensitive to translating objects in horizontal and vertical directions. Though each has been modelled and applied in various visual scenes including robot scenarios, little has been done on investigating their complementary functionality and selectivity when functioning together. To fill this vacancy, we introduce a hybrid model combining two LGMDs (LGMD-1 and LGMD-2) with horizontally (rightward and leftward) sensitive LPTCs (LPTC-R and LPTC-L) specialising in fast collision perception. With coordination and competition between different activated neurons, the proximity feature by frontal approaching stimuli can be largely sharpened up by suppressing translating and receding motions. The proposed method has been implemented in ground micro-mobile robots as embedded systems. The multi-robot experiments have demonstrated the effectiveness and robustness of the proposed model for frontal collision sensing, which outperforms previous single-type neuron computation methods against translating interference.

According to the no-free-lunch theorem, there is no single meta-heuristic algorithm that can optimally solve all optimization problems. This motivates many researchers to continuously develop new optimization algorithms. In this paper, a novel nature-inspired meta-heuristic optimization algorithm called virus spread optimization (VSO) is proposed. VSO loosely mimics the spread of viruses among hosts, and can be effectively applied to solving many challenging and continuous optimization problems. We devise a new representation scheme and viral operations that are radically different from previously proposed virus-based optimization algorithms. First, the viral RNA of each host in VSO denotes a potential solution for which different viral operations will help to diversify the searching strategies in order to largely enhance the solution quality. In addition, an imported infection mechanism, inheriting the searched optima from another colony, is introduced to possibly avoid the prematuration of any potential solution in solving complex problems. VSO has an excellent capability to conduct adaptive neighborhood searches around the discovered optima for achieving better solutions. Furthermore, with a flexible infection mechanism, VSO can quickly escape from local optima. To clearly demonstrate both its effectiveness and efficiency, VSO is critically evaluated on a series of well-known benchmark functions. Moreover, VSO is validated on its applicability through two real-world examples including the financial portfolio optimization and optimization of hyper-parameters of support vector machines for classification problems. The results show that VSO has attained superior performance in terms of solution fitness, convergence rate, scalability, reliability, and flexibility when compared to those results of the conventional as well as state-of-the-art meta-heuristic optimization algorithms.

This paper investigates the feasibility of using Graph Neural Networks (GNNs) for classical motion planning problems. Planning algorithms that search through discrete spaces as well as continuous ones are studied. This paper proposes using GNNs to guide the search algorithm by exploiting the ability of GNNs to extract low level information about the topology of a planning space. We present two techniques, GNNs over dense fixed graphs for low-dimensional problems and sampling-based GNNs for high-dimensional problems. We examine the ability of a GNN to tackle planning problems that are heavily dependent on the topology of the space such as identifying critical nodes, learning a heuristic that guides exploration in $\text{A}^*$, and learning the sampling distribution in Rapidly-exploring Random Trees (RRT). We demonstrate that GNNs can offer better results when compared to traditional analytic methods as well as learning-based approaches that employ fully-connected networks or convolutional neural networks.

Despite the remarkable progress made by the policy gradient algorithms in reinforcement learning (RL), sub-optimal policies usually result from the local exploration property of the policy gradient update. In this work, we propose a method referred to as Zeroth-Order Supervised Policy Improvement (ZOSPI) that exploits the estimated value function Q globally while preserves the local exploitation of the policy gradient methods. We prove that with a good function structure, the zeroth-order optimization strategy combining both local and global samplings can find the global minima within a polynomial number of samples. To improve the exploration efficiency in unknown environments, ZOSPI is further combined with bootstrapped Q networks. Different from the standard policy gradient methods, the policy learning of ZOSPI is conducted in a self-supervision manner so that the policy can be implemented with gradient-free non-parametric models besides the neural network approximator. Experiments show that ZOSPI achieves competitive results on MuJoCo locomotion tasks with a remarkable sample efficiency.

We develop a framework to leverage the elegant "worst average-case" idea in smoothed complexity analysis to social choice, motivated by modern applications of social choice powered by AI and ML. Using our framework, we characterize the smoothed likelihood of some fundamental paradoxes and impossibility theorems as the number of agents increases. For Condrocet's paradox, we prove that the smoothed likelihood of the paradox either vanishes at an exponential rate, or does not vanish at all. For the folklore impossibility on the non-existence of voting rules that satisfy anonymity and neutrality, we characterize the rate for the impossibility to vanish, to be either polynomially fast or exponentially fast. We also propose a novel easy-to-compute tie-breaking mechanism that optimally preserves anonymity and neutrality for even number of alternatives in natural settings. Our results illustrate the smoothed possibility of social choice---even though the paradox and the impossibility theorem hold in the worst case, they may not be a big concern in practice in certain natural settings.

During the last decade, various approaches have been put forward to integrate business processes with different types of data. Each of such approaches reflects specific demands in the whole process-data integration spectrum. One particular important point is the capability of these approaches to flexibly accommodate processes with multiple cases that need to co-evolve. In this work, we introduce and study an extension of coloured Petri nets, called catalog-nets, providing two key features to capture this type of processes. On the one hand, net transitions are equipped with guards that simultaneously inspect the content of tokens and query facts stored in a read-only, persistent database. On the other hand, such transitions can inject data into tokens by extracting relevant values from the database or by generating genuinely fresh ones. We systematically encode catalog-nets into one of the reference frameworks for the (parameterised) verification of data and processes. We show that fresh-value injection is a particularly complex feature to handle, and discuss strategies to tame it. Finally, we discuss how catalog nets relate to well-known formalisms in this area.

The 'old world' instrument, survey, remains a tool of choice for firms to obtain ratings of satisfaction and experience that customers realize while interacting online with firms. While avenues for survey have evolved from emails and links to pop-ups while browsing, the deficiencies persist. These include - reliance on ratings of very few respondents to infer about all customers' online interactions; failing to capture a customer's interactions over time since the rating is a one-time snapshot; and inability to tie back customers' ratings to specific interactions because ratings provided relate to all interactions. To overcome these deficiencies we extract proxy ratings from clickstream data, typically collected for every customer's online interactions, by developing an approach based on Reinforcement Learning (RL). We introduce a new way to interpret values generated by the value function of RL, as proxy ratings. Our approach does not need any survey data for training. Yet, on validation against actual survey data, proxy ratings yield reasonable performance results. Additionally, we offer a new way to draw insights from values of the value function, which allow associating specific interactions to their proxy ratings. We introduce two new metrics to represent ratings - one, customer-level and the other, aggregate-level for click actions across customers. Both are defined around proportion of all pairwise, successive actions that show increase in proxy ratings. This intuitive customer-level metric enables gauging the dynamics of ratings over time and is a better predictor of purchase than customer ratings from survey. The aggregate-level metric allows pinpointing actions that help or hurt experience. In sum, proxy ratings computed unobtrusively from clickstream, for every action, for each customer, and for every session can offer interpretable and more insightful alternative to surveys.

We propose an embodied system based on the free energy principle (FEP) for sensorimotor visual perception. We evaluated it in a character-recognition task using the MNIST dataset. Although the FEP has successfully described a rule that living things obey mathematically and claims that a biological system continues to change its internal models and behaviors to minimize the difference in predicting sensory input, it is not enough to model sensorimotor visual perception. An embodiment of the system is the key to achieving sensorimotor visual perception. The proposed embodied system is configured by a body and memory. The body has an ocular motor system controlling the direction of eye gaze, which means that the eye can only observe a small focused area of the environment. The memory is not photographic, but is a generative model implemented with a variational autoencoder that contains prior knowledge about the environment, and that knowledge is classified. By limiting body and memory abilities and operating according to the FEP, the embodied system repeatedly takes action to obtain the next sensory input based on various potentials of future sensory inputs. In the evaluation, the inference of the environment was represented as an approximate posterior distribution of characters (0 - 9). As the number of repetitions increased, the attention area moved continuously, gradually reducing the uncertainty of characters. Finally, the probability of the correct character became the highest among the characters. Changing the initial attention position provides a different final distribution, suggesting that the proposed system has a confirmation bias.

We study linear contextual bandits with access to a large, partially observable, offline dataset that was sampled from some fixed policy. We show that this problem is closely related to a variant of the bandit problem with side information. We construct a linear bandit algorithm that takes advantage of the projected information, and prove regret bounds. Our results demonstrate the ability to take full advantage of partially observable offline data. Particularly, we prove regret bounds that improve current bounds by a factor related to the visible dimensionality of the contexts in the data. Our results indicate that partially observable offline data can significantly improve online learning algorithms. Finally, we demonstrate various characteristics of our approach through synthetic simulations.

Local structure such as context-specific independence (CSI) has received much attention in the probabilistic graphical model (PGM) literature, as it facilitates the modeling of large complex systems, as well as for reasoning with them. In this paper, we provide a new perspective on how to learn CSIs from data. We propose to first learn a functional and parameterized representation of a conditional probability table (CPT), such as a neural network. Next, we quantize this continuous function, into an arithmetic circuit representation that facilitates efficient inference. In the first step, we can leverage the many powerful tools that have been developed in the machine learning literature. In the second step, we exploit more recently-developed analytic tools from explainable AI, for the purposes of learning CSIs. Finally, we contrast our approach, empirically and conceptually, with more traditional variable-splitting approaches, that search for CSIs more explicitly.