Currently, next location recommendation plays a vital role in location-based social network applications and services. Although many methods have been proposed to solve this problem, three important challenges have not been well addressed so far: (1) most existing methods are based on recurrent network, which is time-consuming to train long sequences due to not allowing for full parallelism; (2) personalized preferences generally are not considered reasonably; (3) existing methods rarely systematically studied how to efficiently utilize various auxiliary information (e.g., user ID and timestamp) in trajectory data and the spatio-temporal relations among non-consecutive locations. To address the above challenges, we propose a novel method named SanMove, a self-attention network based model, to predict the next location via capturing the long- and short-term mobility patterns of users. Specifically, SanMove introduces a long-term preference learning module, and it uses a self-attention module to capture the users long-term mobility pattern which can represent personalized location preferences of users. Meanwhile, SanMove uses a spatial-temporal guided non-invasive self-attention (STNOVA) to exploit auxiliary information to learn short-term preferences. We evaluate SanMove with two real-world datasets, and demonstrate SanMove is not only faster than the state-of-the-art RNN-based predict model but also outperforms the baselines for next location prediction.

Deep reinforcement learning (Deep RL) has recently seen significant progress in developing algorithms for generalization. However, most algorithms target a single type of generalization setting. In this work, we study generalization across three disparate task structures: (a) tasks composed of spatial and temporal compositions of regularly occurring object motions; (b) tasks composed of active perception of and navigation towards regularly occurring 3D objects; and (c) tasks composed of remembering goal-information over sequences of regularly occurring object-configurations. These diverse task structures all share an underlying idea of compositionality: task completion always involves combining recurring segments of task-oriented perception and behavior. We hypothesize that an agent can generalize within a task structure if it can discover representations that capture these recurring task-segments. For our tasks, this corresponds to representations for recognizing individual object motions, for navigation towards 3D objects, and for navigating through object-configurations. Taking inspiration from cognitive science, we term representations for recurring segments of an agent's experience, "perceptual schemas". We propose Feature Attending Recurrent Modules (FARM), which learns a state representation where perceptual schemas are distributed across multiple, relatively small recurrent modules. We compare FARM to recurrent architectures that leverage spatial attention, which reduces observation features to a weighted average over spatial positions. Our experiments indicate that our feature-attention mechanism better enables FARM to generalize across the diverse object-centric domains we study.

While generative adversarial networks (GAN) are popular for their higher sample quality as opposed to other generative models like the variational autoencoders (VAE) and Boltzmann machines, they suffer from the same difficulty of the evaluation of generated samples. Various aspects must be kept in mind, such as the quality of generated samples, the diversity of classes (within a class and among classes), the use of disentangled latent spaces, agreement of said evaluation metric with human perception, etc. In this paper, we propose a new score, namely, GM Score, which takes into various factors such as sample quality, disentangled representation, intra-class and inter-class diversity, and other metrics such as precision, recall, and F1 score are employed for discriminability of latent space of deep belief network (DBN) and restricted Boltzmann machine (RBM). The evaluation is done for different GANs (GAN, DCGAN, BiGAN, CGAN, CoupledGAN, LSGAN, SGAN, WGAN, and WGAN Improved) trained on the benchmark MNIST dataset.

We consider the task of building strong but human-like policies in multi-agent decision-making problems, given examples of human behavior. Imitation learning is effective at predicting human actions but may not match the strength of expert humans, while self-play learning and search techniques (e.g. AlphaZero) lead to strong performance but may produce policies that are difficult for humans to understand and coordinate with. We show in chess and Go that regularizing search policies based on the KL divergence from an imitation-learned policy by applying Monte Carlo tree search produces policies that have higher human prediction accuracy and are stronger than the imitation policy. We then introduce a novel regret minimization algorithm that is regularized based on the KL divergence from an imitation-learned policy, and show that applying this algorithm to no-press Diplomacy yields a policy that maintains the same human prediction accuracy as imitation learning while being substantially stronger.

In this work we continue to build upon recent advances in reinforcement learning for finite Markov processes. A common approach among previous existing algorithms, both single-actor and distributed, is to either clip rewards or to apply a transformation method on Q-functions to handle a large variety of magnitudes in real discounted returns. We theoretically show that one of the most successful methods may not yield an optimal policy if we have a non-deterministic process. As a solution, we argue that distributional reinforcement learning lends itself to remedy this situation completely. By the introduction of a conjugated distributional operator we may handle a large class of transformations for real returns with guaranteed theoretical convergence. We propose an approximating single-actor algorithm based on this operator that trains agents directly on unaltered rewards using a proper distributional metric given by the Cram\'er distance. To evaluate its performance in a stochastic setting we train agents on a suite of 55 Atari 2600 games using sticky-actions and obtain state-of-the-art performance compared to other well-known algorithms in the Dopamine framework.

Single-Agent (SA) Reinforcement Learning systems have shown outstanding results on non-stationary problems. However, Multi-Agent Reinforcement Learning (MARL) can surpass SA systems generally and when scaling. Furthermore, MA systems can be super-powered by collaboration, which can happen through observing others, or a communication system used to share information between collaborators. Here, we developed a distributed MA learning mechanism with the ability to communicate based on decentralised partially observable Markov decision processes (Dec-POMDPs) and Graph Neural Networks (GNNs). Minimising the time and energy consumed by training Machine Learning models while improving performance can be achieved by collaborative MA mechanisms. We demonstrate this in a real-world scenario, an offshore wind farm, including a set of distributed wind turbines, where the objective is to maximise collective efficiency. Compared to a SA system, MA collaboration has shown significantly reduced training time and higher cumulative rewards in unseen and scaled scenarios.

Controllers for autonomous systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modelled as process noise, and common assumptions are that the underlying distributions are known and/or Gaussian. In practice, however, these assumptions may be unrealistic and can lead to poor approximations of the true noise distribution. We present a novel planning method that does not rely on any explicit representation of the noise distributions. In particular, we address the problem of computing a controller that provides probabilistic guarantees on safely reaching a target. First, we abstract the continuous system into a discrete-state model that captures noise by probabilistic transitions between states. As a key contribution, we adapt tools from the scenario approach to compute probably approximately correct (PAC) bounds on these transition probabilities, based on a finite number of samples of the noise. We capture these bounds in the transition probability intervals of a so-called interval Markov decision process (iMDP). This iMDP is robust against uncertainty in the transition probabilities, and the tightness of the probability intervals can be controlled through the number of samples. We use state-of-the-art verification techniques to provide guarantees on the iMDP, and compute a controller for which these guarantees carry over to the autonomous system. Realistic benchmarks show the practical applicability of our method, even when the iMDP has millions of states or transitions.

Andrei Markov didn't agree with Pavel Nekrasov, when he said independence between variables was necessary for the Weak Law of Large Numbers to be applied. When you collect independent samples, as the number of samples gets bigger, the mean of those samples converges to the true mean of the population. But Markov believed independence was not a necessary condition for the mean to converge. So he set out to define how the average of the outcomes from a process involving dependent random variables could converge over time. Thanks to this intellectual disagreement, Markov created a way to describe how random, also called stochastic, systems or processes evolve over time.

Population-level societal events, such as civil unrest and crime, often have a significant impact on our daily life. Forecasting such events is of great importance for decision-making and resource allocation. Event prediction has traditionally been challenging due to the lack of knowledge regarding the true causes and underlying mechanisms of event occurrence. In recent years, research on event forecasting has made significant progress due to two main reasons: (1) the development of machine learning and deep learning algorithms and (2) the accessibility of public data such as social media, news sources, blogs, economic indicators, and other meta-data sources. The explosive growth of data and the remarkable advancement in software/hardware technologies have led to applications of deep learning techniques in societal event studies. This paper is dedicated to providing a systematic and comprehensive overview of deep learning technologies for societal event predictions. We focus on two domains of societal events: \textit{civil unrest} and \textit{crime}. We first introduce how event forecasting problems are formulated as a machine learning prediction task. Then, we summarize data resources, traditional methods, and recent development of deep learning models for these problems. Finally, we discuss the challenges in societal event forecasting and put forward some promising directions for future research.

Generation and analysis of time-series data is relevant to many quantitative fields ranging from economics to fluid mechanics. In the physical sciences, structures such as metastable and coherent sets, slow relaxation processes, collective variables, dominant transition pathways or manifolds and channels of probability flow can be of great importance for understanding and characterizing the kinetic, thermodynamic and mechanistic properties of the system. Deeptime is a general purpose Python library offering various tools to estimate dynamical models based on time-series data including conventional linear learning methods, such as Markov state models (MSMs), Hidden Markov Models and Koopman models, as well as kernel and deep learning approaches such as VAMPnets and deep MSMs. The library is largely compatible with scikit-learn, having a range of Estimator classes for these different models, but in contrast to scikit-learn also provides deep Model classes, e.g. in the case of an MSM, which provide a multitude of analysis methods to compute interesting thermodynamic, kinetic and dynamical quantities, such as free energies, relaxation times and transition paths. The library is designed for ease of use but also easily maintainable and extensible code. In this paper we introduce the main features and structure of the deeptime software.