Many multiagent applications require an agent to learn quickly how to interact with previously unknown other agents. To address this problem, researchers have studied learning algorithms which compute posterior beliefs over a hypothesised set of policies, based on the observed actions of the other agents. The posterior belief is complemented by the prior belief, which specifies the subjective likelihood of policies before any actions are observed. In this paper, we present the first comprehensive empirical study on the practical impact of prior beliefs over policies in repeated interactions. We show that prior beliefs can have a significant impact on the long-term performance of such methods, and that the magnitude of the impact depends on the depth of the planning horizon. Moreover, our results demonstrate that automatic methods can be used to compute prior beliefs with consistent performance effects. This indicates that prior beliefs could be eliminated as a manual parameter and instead be computed automatically.

In this work we consider the problem of path planning for an autonomous vehicle that moves on a freeway. The most common approaches that are used to address this problem are based on optimal control methods, which make assumptions about the model of the environment and the system dynamics. On the contrary, we propose the development of a driving policy based on reinforcement learning. In this way, the proposed driving policy makes minimal or no assumptions about the environment, since a priori knowledge about the system dynamics is not required. We consider driving scenarios where the road is occupied both by autonomous and manual driving vehicles. To the best of our knowledge, this is one of the first approaches that propose a reinforcement learning driving policy for mixed driving environments. The derived reinforcement learning policy, firstly, is compared against an optimal policy derived via dynamic programming, and, secondly, its efficiency is evaluated under realistic scenarios generated by the established SUMO microscopic traffic flow simulator. Finally, we present some initial results regarding the effect of autonomous vehicles' behavior on the overall traffic flow.

Parking, matching, scheduling, and routing are common problems in train maintenance. In particular, train units are commonly maintained and cleaned at dedicated shunting yards. The planning problem that results from such situations is referred to as the Train Unit Shunting Problem (TUSP). This problem involves matching arriving train units to service tasks and determining the schedule for departing trains. The TUSP is an important problem as it is used to determine the capacity of shunting yards and arises as a sub-problem of more general scheduling and planning problems. In this paper, we consider the case of the Dutch Railways (NS) TUSP. As the TUSP is complex, NS currently uses a local search (LS) heuristic to determine if an instance of the TUSP has a feasible solution. Given the number of shunting yards and the size of the planning problems, improving the evaluation speed of the LS brings significant computational gain. In this work, we use a machine learning approach that complements the LS and accelerates the search process. We use a Deep Graph Convolutional Neural Network (DGCNN) model to predict the feasibility of solutions obtained during the run of the LS heuristic. We use this model to decide whether to continue or abort the search process. In this way, the computation time is used more efficiently as it is spent on instances that are more likely to be feasible. Using simulations based on real-life instances of the TUSP, we show how our approach improves upon the previous method on prediction accuracy and leads to computational gains for the decision-making process.

Probabilistic logic reasoning is a central component of such cognitive architectures as OpenCog. However, as an integrative architecture, OpenCog facilitates cognitive synergy via hybridization of different inference methods. In this paper, we introduce a differentiable version of Probabilistic Logic networks, which rules operate over tensor truth values in such a way that a chain of reasoning steps constructs a computation graph over tensors that accepts truth values of premises from the knowledge base as input and produces truth values of conclusions as output. This allows for both learning truth values of premises and formulas for rules (specified in a form with trainable weights) by backpropagation combining subsymbolic optimization and symbolic reasoning.

In this paper, we argue that competitive pressures could incentivize AI companies to underinvest in ensuring their systems are safe, secure, and have a positive social impact. Ensuring that AI systems are developed responsibly may therefore require preventing and solving collective action problems between companies. We note that there are several key factors that improve the prospects for cooperation in collective action problems. We use this to identify strategies to improve the prospects for industry cooperation on the responsible development of AI.

Decentralized swarm robotic solutions to searching for targets that emit a spatially varying signal promise task parallelism, time efficiency, and fault tolerance. It is, however, challenging for swarm algorithms to offer scalability and efficiency, while preserving mathematical insights into the exhibited behavior. A new decentralized search method (called Bayes-Swarm), founded on batch Bayesian Optimization (BO) principles, is presented here to address these challenges. Unlike swarm heuristics approaches, Bayes-Swarm decouples the knowledge generation and task planning process, thus preserving insights into the emergent behavior. Key contributions lie in: 1) modeling knowledge extraction over trajectories, unlike in BO; 2) time-adaptively balancing exploration/exploitation and using an efficient local penalization approach to account for potential interactions among different robots' planned samples; and 3) presenting an asynchronous implementation of the algorithm. This algorithm is tested on case studies with bimodal and highly multimodal signal distributions. Up to 76 times better efficiency is demonstrated compared to an exhaustive search baseline. The benefits of exploitation/exploration balancing, asynchronous planning, and local penalization, and scalability with swarm size, are also demonstrated.

Recently, there has been much research into modelling of uncertainty in human perception through Fuzzy Sets (FSs). Most of this research has focused on allowing respondents to express their (intra) uncertainty using intervals. Here, depending on the technique used and types of uncertainties being modelled different types of FSs can be obtained (e.g., Type-1, Interval Type-2, General Type-2). Arguably, one of the most flexible techniques is the Interval Agreement Approach (IAA) as it allows to model the perception of all respondents without making assumptions such as outlier removal or predefined membership function types (e.g. Gaussian). A key aspect in the analysis of interval-valued data and indeed, IAA based agreement models of said data, is to determine the position and strengths of agreement across all the sources/participants. While previously, the Agreement Ratio was proposed to measure the strength of agreement in fuzzy set based models of interval data, said measure has only been applicable to type-1 fuzzy sets. In this paper, we extend the Agreement Ratio to capture the degree of inter-group agreement modelled by a General Type-2 Fuzzy Set when using the IAA. This measure relies on using a similarity measure to quantitatively express the relation between the different levels of agreement in a given FS. Synthetic examples are provided in order to demonstrate both behaviour and calculation of the measure. Finally, an application to real-world data is provided in order to show the potential of this measure to assess the divergence of opinions for ambiguous concepts when heterogeneous groups of participants are involved.

Model compression provides a means to efficiently deploy deep neural networks (DNNs) on devices that limited computation resources and tight power budgets, such as mobile and IoT (Internet of Things) devices. Consequently, model compression is one of the most critical topics in modern deep learning. Typically, the state-of-the-art model compression methods suffer from a big limitation: they are only based on heuristics rather than theoretical foundation and thus offer no worst-case guarantees. To bridge this gap, Baykal et. al. [2018a] suggested using a coreset, a small weighted subset of the data that provably approximates the original data set, to sparsify the parameters of a trained fully-connected neural network by sampling a number of neural network parameters based on the importance of the data. However, the sampling procedure is data-dependent and can only be only be performed after an expensive training phase. We propose the use of data-independent coresets to perform provable model compression without the need for training. We first prove that there exists a coreset whose size is independent of the input size of the data for any neuron whose activation function is from a family of functions that includes variants of ReLU, sigmoid and others. We then provide a compression-based algorithm that constructs these coresets and explicitly applies neuron pruning for the underlying model. We demonstrate the effectiveness of our methods with experimental evaluations for both synthetic and real-world benchmark network compression. In particular, our framework provides up to 90% compression on the LeNet-300-100 architecture on MNIST and actually improves the accuracy.

The application of biomechanic and motor control models in the control of bidedal robots (humanoids, and exoskeletons) has revealed limitations of our understanding of human locomotion. A recently proposed model uses the potential energy for bipedal structures to model the bipedal dynamics, and it allows to predict the system dynamics from its kinematics. This work proposes a task-space planner for human-like straight locomotion that target application of in rehabilitation robotics and computational neuroscience. The proposed architecture is based on the potential energy model and employs locomotor strategies from human data as a reference for human behaviour. The model generates Centre of Mass (CoM) trajectories, foot swing trajectories and the Base of Support (BoS) over time. The data show that the proposed architecture can generate behaviour in line with human walking strategies for both the CoM and the foot swing. Despite the CoM vertical trajectory being not as smooth as a human trajectory, yet the proposed model significantly reduces the error in the estimation of the CoM vertical trajectory compared to the inverted pendulum models. The proposed model is also able to asses the stability based on the body kinematics embedding in currently used in the clinical practice. However, the model also implies a shift in the interpretation of the spatiotemporal parameters of the gait, which are now determined by the conditions for the equilibrium and not \textit{vice versa}. In other words, locomotion is a dynamic reaching where the motor primitives are also determined by gravity.

Language modelling has been an integral part of providing an understanding of the nature of language to capture its meaning. In order to improve the machine understanding of language using sequential models, we seek to explore two prominent areas of statistical language models, the Hidden Markov Model (HMM), and a Recurrent Neural Network (RNN) architecture, known commonly as Long Short-Term Memory (LSTM). Under a discrete stochastic modelling framework, HMM's were first introduced in Rabiner [1] to classify speech signals. First used to automate AT&T's voice activated call center, the revolutionary technology allowed computers to robustly characterise speech, and form a basic understanding of spoken words. HMM's have since become a definitive benchmark for the state-of-the-art for speech recognition, and text recognition. Around the same period, RNN's were introduced by Rumelhart et al. [2], however, the training complexity of the model was far too high and not commensurate with the hardware capabilities at the time. In the 21st century, With the introduction of more advanced hardware for deep learning model training, came a wave of applications for the RNN for both voice, text recognition, [3], [4], [5] and machine translation [6]. In parallel, an early form of neural language model was developed in Bengio et al. [7], displaying promising results in statistical language modelling. LSTM's were the first introduced in Hochreiter and Schmidhuber [8], specifically to combat the vanishing gradient problem, which will be further addressed in Section 1.2.