We introduce the forward-backward (FB) representation of the dynamics of a reward-free Markov decision process. It provides explicit near-optimal policies for any reward specified a posteriori. During an unsupervised phase, we use reward-free interactions with the environment to learn two representations via off-the-shelf deep learning methods and temporal difference (TD) learning. In the test phase, a reward representation is estimated either from observations or an explicit reward description (e.g., a target state). The optimal policy for that reward is directly obtained from these representations, with no planning. The unsupervised FB loss is well-principled: if training is perfect, the policies obtained are provably optimal for any reward function. With imperfect training, the sub-optimality is proportional to the unsupervised approximation error. The FB representation learns long-range relationships between states and actions, via a predictive occupancy map, without having to synthesize states as in model-based approaches. This is a step towards learning controllable agents in arbitrary black-box stochastic environments. This approach compares well to goal-oriented RL algorithms on discrete and continuous mazes, pixel-based MsPacman, and the FetchReach virtual robot arm. We also illustrate how the agent can immediately adapt to new tasks beyond goal-oriented RL.

The building sector consumes the largest energy in the world, and there have been considerable research interests in energy consumption and comfort management of buildings. Inspired by recent advances in reinforcement learning (RL), this paper aims at assessing the potential of RL in building climate control problems with occupant interaction. We apply a recent RL approach, called DDPG (deep deterministic policy gradient), for the continuous building control tasks and assess its performance with simulation studies in terms of its ability to handle (a) the partial state observability due to sensor limitations; (b) complex stochastic system with high-dimensional state-spaces, which are jointly continuous and discrete; (c) uncertainties due to ambient weather conditions, occupant's behavior, and comfort feelings. Especially, the partial observability and uncertainty due to the occupant interaction significantly complicate the control problem. Through simulation studies, the policy learned by DDPG demonstrates reasonable performance and computational tractability.

Reinforcement learning agents have demonstrated remarkable achievements in simulated environments. Data efficiency poses an impediment to carrying this success over to real environments. The design of data-efficient agents calls for a deeper understanding of information acquisition and representation. We develop concepts and establish a regret bound that together offer principled guidance. The bound sheds light on questions of what information to seek, how to seek that information, and what information to retain. To illustrate concepts, we design simple agents that build on them and present computational results that demonstrate improvements in data efficiency. Other learning paradigms are about minimization; reinforcement learning is about maximization.

Natural language processing (NLP) and deep learning are growing in popularity for their use in ML technologies like self-driving cars and speech recognition software. As more companies begin to implement deep learning components and other machine learning practices, the demand for software developers and data scientists with proficiency in deep learning is skyrocketing. Today, we will introduce you to a popular deep learning project, the Text Generator, to familiarize you with important, industry-standard NLP concepts, including Markov chains. By the end of this article, you'll understand how to build a Text Generator component for search engine systems and know how to implement Markov chains for faster predictive models.

We review our recent work in the area of autonomous materials research, highlighting the coupling of machine learning methods and models and more problem-aware modeling. We review the general Bayesian framework for closed-loop design employed by many autonomous materials platforms. We then provide examples of our work on such platforms. We finally review our approaches to extend current statistical and ML models to better reflect problem-specific structure including the use of physics-based models and incorporation of operational considerations into the decision-making procedure.

In this paper, we present new image segmentation methods based on hidden Markov random fields (HMRFs) and cuckoo search (CS) variants. HMRFs model the segmentation problem as a minimization of an energy function. CS algorithm is one of the recent powerful optimization techniques. Therefore, five variants of the CS algorithm are used to compute a solution. Through tests, we conduct a study to choose the CS variant with parameters that give good results (execution time and quality of segmentation). CS variants are evaluated and compared with non-destructive testing (NDT) images using a misclassification error (ME) criterion.

Feature selection is an important problem in machine learning, which aims to select variables that lead to an optimal predictive model. In this paper, we focus on feature selection for post-intervention outcome prediction from pre-intervention variables. We are motivated by healthcare settings, where the goal is often to select the treatment that will maximize a specific patient's outcome; however, we often do not have sufficient randomized control trial data to identify well the conditional treatment effect. We show how we can use observational data to improve feature selection and effect estimation in two cases: (a) using observational data when we know the causal graph, and (b) when we do not know the causal graph but have observational and limited experimental data. Our paper extends the notion of Markov boundary to treatment-outcome pairs. We provide theoretical guarantees for the methods we introduce. In simulated data, we show that combining observational and experimental data improves feature selection and effect estimation.

Digital twins are emerging in many industries, typically consisting of simulation models and data associated with a specific physical system. One of the main reasons for developing a digital twin, is to enable the simulation of possible consequences of a given action, without the need to interfere with the physical system itself. Physical systems of interest, and the environments they operate in, do not always behave deterministically. Moreover, information about the system and its environment is typically incomplete or imperfect. Probabilistic representations of systems and environments may therefore be called for, especially to support decisions in application areas where actions may have severe consequences. In this paper we introduce the probabilistic digital twin (PDT). We will start by discussing how epistemic uncertainty can be treated using measure theory, by modelling epistemic information via $\sigma$-algebras. Based on this, we give a formal definition of how epistemic uncertainty can be updated in a PDT. We then study the problem of optimal sequential decision making. That is, we consider the case where the outcome of each decision may inform the next. Within the PDT framework, we formulate this optimization problem. We discuss how this problem may be solved (at least in theory) via the maximum principle method or the dynamic programming principle. However, due to the curse of dimensionality, these methods are often not tractable in practice. To mend this, we propose a generic approximate solution using deep reinforcement learning together with neural networks defined on sets. We illustrate the method on a practical problem, considering optimal information gathering for the estimation of a failure probability.

We constructed a hippocampal formation (HPF)-inspired probabilistic generative model (HPF-PGM) using the structure-constrained interface decomposition method. By modeling brain regions with PGMs, this model is positioned as a module that can be integrated as a whole-brain PGM. We discuss the relationship between simultaneous localization and mapping (SLAM) in robotics and the findings of HPF in neuroscience. Furthermore, we survey the modeling for HPF and various computational models, including brain-inspired SLAM, spatial concept formation, and deep generative models. The HPF-PGM is a computational model that is highly consistent with the anatomical structure and functions of the HPF, in contrast to typical conventional SLAM models. By referencing the brain, we suggest the importance of the integration of egocentric/allocentric information from the entorhinal cortex to the hippocampus and the use of discrete-event queues.

With the worldwide population booming, the healthcare industry must adapt and develop the most innovative technologies to gather and analyze such massive clinical data and information about patients. It's about bringing in machine learning (ML) and artificial intelligence (AI) to make the real-world healthcare system high-powered and error-free. In 2017, Google developed an algorithm that can detect diseases, such as cancer, with 89% accuracy. Three years later, in 2020, smartphone-based mental healthcare apps are becoming the biggest buzzword, thanks to digital behavioral solutions, and machine learning in healthcare has just started. The purpose of ML in healthcare is to minimize human error without limiting the human factor.