Score following is the process of tracking a musical performance (audio) with respect to a known symbolic representation (a score). We start this paper by formulating score following as a multimodal Markov Decision Process, the mathematical foundation for sequential decision making. Given this formal definition, we address the score following task with state-of-the-art deep reinforcement learning (RL) algorithms such as synchronous advantage actor critic (A2C). In particular, we design multimodal RL agents that simultaneously learn to listen to music, read the scores from images of sheet music, and follow the audio along in the sheet, in an end-to-end fashion. All this behavior is learned entirely from scratch, based on a weak and potentially delayed reward signal that indicates to the agent how close it is to the correct position in the score. Besides discussing the theoretical advantages of this learning paradigm, we show in experiments that it is in fact superior compared to previously proposed methods for score following in raw sheet music images.

Recently, deep reinforcement learning (RL) methods have been applied successfully to multi-agent scenarios. Typically, these methods rely on a concatenation of agent states to represent the information content required for decentralized decision making. However, concatenation scales poorly to swarm systems with a large number of homogeneous agents as it does not exploit the fundamental properties inherent to these systems: (i) the agents in the swarm are interchangeable and (ii) the exact number of agents in the swarm is irrelevant. Therefore, we propose a new state representation for deep multi-agent RL based on mean embeddings of distributions. We treat the agents as samples of a distribution and use the empirical mean embedding as input for a decentralized policy. We define different feature spaces of the mean embedding using histograms, radial basis functions and a neural network learned end-to-end. We evaluate the representation on two well known problems from the swarm literature (rendezvous and pursuit evasion), in a globally and locally observable setup. For the local setup we furthermore introduce simple communication protocols. Of all approaches, the mean embedding representation using neural network features enables the richest information exchange between neighboring agents facilitating the development of more complex collective strategies.

In several real-world domains it is required to plan ahead while there are finite resources available for executing the plan. The limited availability of resources imposes constraints on the plans that can be executed, which need to be taken into account while computing a plan. A Constrained Partially Observable Markov Decision Process (Constrained POMDP) can be used to model resource-constrained planning problems which include uncertainty and partial observability. Constrained POMDPs provide a framework for computing policies which maximize expected reward, while respecting constraints on a secondary objective such as cost or resource consumption. Column generation for linear programming can be used to obtain Constrained POMDP solutions. This method incrementally adds columns to a linear program, in which each column corresponds to a POMDP policy obtained by solving an unconstrained subproblem. Column generation requires solving a potentially large number of POMDPs, as well as exact evaluation of the resulting policies, which is computationally difficult. We propose a method to solve subproblems in a two-stage fashion using approximation algorithms. First, we use a tailored point-based POMDP algorithm to obtain an approximate subproblem solution. Next, we convert this approximate solution into a policy graph, which we can evaluate efficiently. The resulting algorithm is a new approximate method for Constrained POMDPs in single-agent settings, but also in settings in which multiple independent agents share a global constraint. Experiments based on several domains show that our method outperforms the current state of the art.

Which authors of this paper are endorsers? Disable MathJax (What is MathJax?)

Roderick Bloem TU Graz Austria A prominent problem in artificial intelligence and machine learning is the safe exploration of an environment. In particular, reinforcement learning is a wellknown technique to determine optimal policies for complicated dynamic systems, but suffers from the fact that such policies may induce harmful behavior. We present the concept of a shield that forces decision-making to provably adhere to safety requirements with high probability. Our method exploits the inherent uncertainties in scenarios given by Markov decision processes. We present a method to compute probabilities of decision making regarding temporal logic constraints. We use that information to realize a shield that--when applied to a reinforcement learning algorithm--ensures (near-)optimal behavior both for the safety constraints and for the actual learning objective. In our experiments, we show on the arcade game PAC-MAN that the learning efficiency increases as the learning needs orders of magnitude fewer episodes. We show tradeoffs between sufficient progress in exploration of the environment and ensuring strict safety.

It is the focus of this work to extend and study the previously proposed quantum-like Bayesian networks to deal with decision-making scenarios by incorporating the notion of maximum expected utility in influence diagrams. The general idea is to take advantage of the quantum interference terms produced in the quantum-like Bayesian Network to influence the probabilities used to compute the expected utility of some action. This way, we are not proposing a new type of expected utility hypothesis. On the contrary, we are keeping it under its classical definition. We are only incorporating it as an extension of a probabilistic graphical model in a compact graphical representation called an influence diagram in which the utility function depends on the probabilistic influences of the quantum-like Bayesian network. Our findings suggest that the proposed quantum-like influence digram can indeed take advantage of the quantum interference effects of quantum-like Bayesian Networks to maximise the utility of a cooperative behaviour in detriment of a fully rational defect behaviour under the prisoner's dilemma game.

This paper introduces a new sparse spatio-temporal structured Gaussian process regression framework for online and offline Bayesian inference. This is the first framework that gives a time-evolving representation of the interdependencies between the components of the sparse signal of interest. A hierarchical Gaussian process describes such structure and the interdependencies are represented via the covariance matrices of the prior distributions. The inference is based on the expectation propagation method and the theoretical derivation of the posterior distribution is provided in the paper. The inference framework is thoroughly evaluated over synthetic, real video and electroencephalography (EEG) data where the spatio-temporal evolving patterns need to be reconstructed with high accuracy. It is shown that it achieves 15% improvement of the F-measure compared with the alternating direction method of multipliers, spatio-temporal sparse Bayesian learning method and one-level Gaussian process model. Additionally, the required memory for the proposed algorithm is less than in the one-level Gaussian process model. This structured sparse regression framework is of broad applicability to source localisation and object detection problems with sparse signals.

Evidence in probabilistic reasoning may be `hard' or `soft', that is, it may be of yes/no form, or it may involve a strength of belief, in the unit interval [0,1]. Reasoning with soft, $[0,1]$-valued evidence is important in many situations but may lead to different, confusing interpretations. This paper intends to bring more mathematical clarity to the field by shifting the existing focus from specification of soft evidence to accomodation of soft evidence. There are two main approaches, known as Jeffrey's rule and Pearl's method, which give different outcomes on soft evidence. This paper describes these two approaches as different ways of updating with soft evidence, highlighting their differences, similarities and applications. This account is based on a novel channel-based approach to Bayesian probability. Proper understanding of these two update mechanisms is highly relevant for inference, decision tools and probabilistic programming languages.

The field of statistical relational learning aims at unifying logic and probability to reason and learn from data. Perhaps the most successful paradigm in the field is probabilistic logic programming: the enabling of stochastic primitives in logic programming, which is now increasingly seen to provide a declarative background to complex machine learning applications. While many systems offer inference capabilities, the more significant challenge is that of learning meaningful and interpretable symbolic representations from data. In that regard, inductive logic programming and related techniques have paved much of the way for the last few decades. Unfortunately, a major limitation of this exciting landscape is that much of the work is limited to finite-domain discrete probability distributions. Recently, a handful of systems have been extended to represent and perform inference with continuous distributions. The problem, of course, is that classical solutions for inference are either restricted to well-known parametric families (e.g., Gaussians) or resort to sampling strategies that provide correct answers only in the limit. When it comes to learning, moreover, inducing representations remains entirely open, other than "data-fitting" solutions that force-fit points to aforementioned parametric families. In this paper, we take the first steps towards inducing probabilistic logic programs for continuous and mixed discrete-continuous data, without being pigeon-holed to a fixed set of distribution families. Our key insight is to leverage techniques from piecewise polynomial function approximation theory, yielding a principled way to learn and compositionally construct density functions. We test the framework and discuss the learned representations.

Classifying the complexity of arithmetic computations is a crucial endeavour in theoretical computer science. Particularly interesting are the decidability and complexity issues pertaining to iterative arithmetic computations, i.e. computations consisting of a repeated application of some set of arithmetic operations on some initial value. Examples of such problems include matrix powering over various semirings [16, 9], the Skolem problem ("Does a given linear recurrent sequence contain a zero term?") and its variants [26, 27, 6], or the related Orbit problem [21, 4]. It is often natural to consider bounded or finite-horizon variants of the problems, which ask, given a time horizon H, whether a certain property holds within the first H iterations of the computation [9]. In this paper, we study the complexity of finite-horizon arithmetic computations arising in algorithmic decision making and operations research.