Deep reinforcement learning has gathered much attention recently. Impressive results were achieved in activities as diverse as autonomous driving, game playing, molecular recombination, and robotics. In all these fields, computer programs have taught themselves to solve difficult problems. They have learned to fly model helicopters and perform aerobatic manoeuvers such as loops and rolls. In some applications they have even become better than the best humans, such as in Atari, Go, poker and StarCraft. The way in which deep reinforcement learning explores complex environments reminds us of how children learn, by playfully trying out things, getting feedback, and trying again. The computer seems to truly possess aspects of human learning; this goes to the heart of the dream of artificial intelligence. The successes in research have not gone unnoticed by educators, and universities have started to offer courses on the subject. The aim of this book is to provide a comprehensive overview of the field of deep reinforcement learning. The book is written for graduate students of artificial intelligence, and for researchers and practitioners who wish to better understand deep reinforcement learning methods and their challenges. We assume an undergraduate-level of understanding of computer science and artificial intelligence; the programming language of this book is Python. We describe the foundations, the algorithms and the applications of deep reinforcement learning. We cover the established model-free and model-based methods that form the basis of the field. Developments go quickly, and we also cover advanced topics: deep multi-agent reinforcement learning, deep hierarchical reinforcement learning, and deep meta learning.

The ability to recover from an unexpected external perturbation is a fundamental motor skill in bipedal locomotion. An effective response includes the ability to not just recover balance and maintain stability but also to fall in a safe manner when balance recovery is physically infeasible. For robots associated with bipedal locomotion, such as humanoid robots and assistive robotic devices that aid humans in walking, designing controllers which can provide this stability and safety can prevent damage to robots or prevent injury related medical costs. This is a challenging task because it involves generating highly dynamic motion for a high-dimensional, non-linear and under-actuated system with contacts. Despite prior advancements in using model-based and optimization methods, challenges such as requirement of extensive domain knowledge, relatively large computational time and limited robustness to changes in dynamics still make this an open problem. In this thesis, to address these issues we develop learning-based algorithms capable of synthesizing push recovery control policies for two different kinds of robots : Humanoid robots and assistive robotic devices that assist in bipedal locomotion. Our work can be branched into two closely related directions : 1) Learning safe falling and fall prevention strategies for humanoid robots and 2) Learning fall prevention strategies for humans using a robotic assistive devices. To achieve this, we introduce a set of Deep Reinforcement Learning (DRL) algorithms to learn control policies that improve safety while using these robots.

We deal with Bayesian generative and discriminative classifiers. Given a model distribution $p(x, y)$, with the observation $y$ and the target $x$, one computes generative classifiers by firstly considering $p(x, y)$ and then using the Bayes rule to calculate $p(x | y)$. A discriminative model is directly given by $p(x | y)$, which is used to compute discriminative classifiers. However, recent works showed that the Bayesian Maximum Posterior classifier defined from the Naive Bayes (NB) or Hidden Markov Chain (HMC), both generative models, can also match the discriminative classifier definition. Thus, there are situations in which dividing classifiers into "generative" and "discriminative" is somewhat misleading. Indeed, such a distinction is rather related to the way of computing classifiers, not to the classifiers themselves. We present a general theoretical result specifying how a generative classifier induced from a generative model can also be computed in a discriminative way from the same model. Examples of NB and HMC are found again as particular cases, and we apply the general result to two original extensions of NB, and two extensions of HMC, one of which being original. Finally, we shortly illustrate the interest of the new discriminative way of computing classifiers in the Natural Language Processing (NLP) framework.

Centralized Training for Decentralized Execution, where training is done in a centralized offline fashion, has become a popular solution paradigm in Multi-Agent Reinforcement Learning. Many such methods take the form of actor-critic with state-based critics, since centralized training allows access to the true system state, which can be useful during training despite not being available at execution time. State-based critics have become a common empirical choice, albeit one which has had limited theoretical justification or analysis. In this paper, we show that state-based critics can introduce bias in the policy gradient estimates, potentially undermining the asymptotic guarantees of the algorithm. We also show that, even if the state-based critics do not introduce any bias, they can still result in a larger gradient variance, contrary to the common intuition. Finally, we show the effects of the theories in practice by comparing different forms of centralized critics on a wide range of common benchmarks, and detail how various environmental properties are related to the effectiveness of different types of critics.

In this paper, we use concepts from supervisory control theory of discrete event systems to propose a method to learn optimal control policies for a finite-state Markov Decision Process (MDP) in which (only) certain sequences of actions are deemed unsafe (respectively safe). We assume that the set of action sequences that are deemed unsafe and/or safe are given in terms of a finite-state automaton; and propose a supervisor that disables a subset of actions at every state of the MDP so that the constraints on action sequence are satisfied. Then we present a version of the Q-learning algorithm for learning optimal policies in the presence of non-Markovian action-sequence and state constraints, where we use the development of reward machines to handle the state constraints. We illustrate the method using an example that captures the utility of automata-based methods for non-Markovian state and action specifications for reinforcement learning and show the results of simulations in this setting.

Stochastic and soft optimal policies resulting from entropy-regularized Markov decision processes (ER-MDP) are desirable for exploration and imitation learning applications. Motivated by the fact that such policies are sensitive with respect to the state transition probabilities, and the estimation of these probabilities may be inaccurate, we study a robust version of the ER-MDP model, where the stochastic optimal policies are required to be robust with respect to the ambiguity in the underlying transition probabilities. Our work is at the crossroads of two important schemes in reinforcement learning (RL), namely, robust MDP and entropy regularized MDP. We show that essential properties that hold for the non-robust ER-MDP and robust unregularized MDP models also hold in our settings, making the robust ER-MDP problem tractable. We show how our framework and results can be integrated into different algorithmic schemes including value or (modified) policy iteration, which would lead to new robust RL and inverse RL algorithms to handle uncertainties. Analyses on computational complexity and error propagation under conventional uncertainty settings are also provided.

Leveraging autonomous systems in safety-critical scenarios requires verifying their behaviors in the presence of uncertainties and black-box components that influence the system dynamics. In this article, we develop a framework for verifying partially-observable, discrete-time dynamical systems with unmodelled dynamics against temporal logic specifications from a given input-output dataset. The verification framework employs Gaussian process (GP) regression to learn the unknown dynamics from the dataset and abstract the continuous-space system as a finite-state, uncertain Markov decision process (MDP). This abstraction relies on space discretization and transition probability intervals that capture the uncertainty due to the error in GP regression by using reproducible kernel Hilbert space analysis as well as the uncertainty induced by discretization. The framework utilizes existing model checking tools for verification of the uncertain MDP abstraction against a given temporal logic specification. We establish the correctness of extending the verification results on the abstraction to the underlying partially-observable system. We show that the computational complexity of the framework is polynomial in the size of the dataset and discrete abstraction. The complexity analysis illustrates a trade-off between the quality of the verification results and the computational burden to handle larger datasets and finer abstractions. Finally, we demonstrate the efficacy of our learning and verification framework on several case studies with linear, nonlinear, and switched dynamical systems.

Besides entity-centric knowledge, usually organized as Knowledge Graph (KG), events are also an essential kind of knowledge in the world, which trigger the spring up of event-centric knowledge representation form like Event KG (EKG). It plays an increasingly important role in many machine learning and artificial intelligence applications, such as intelligent search, question-answering, recommendation, and text generation. This paper provides a comprehensive survey of EKG from history, ontology, instance, and application views. Specifically, to characterize EKG thoroughly, we focus on its history, definitions, schema induction, acquisition, related representative graphs/systems, and applications. The development processes and trends are studied therein. We further summarize perspective directions to facilitate future research on EKG.

The burgeoning of AI has prompted recommendations that AI techniques should be "human-centered". However, there is no clear definition of what is meant by Human Centered Artificial Intelligence, or for short, HCAI. This paper aims to improve this situation by addressing some foundational aspects of HCAI. To do so, we introduce the term HCAI agent to refer to any physical or software computational agent equipped with AI components and that interacts and/or collaborates with humans. This article identifies five main conceptual components that participate in an HCAI agent: Observations, Requirements, Actions, Explanations and Models. We see the notion of HCAI agent, together with its components and functions, as a way to bridge the technical and non-technical discussions on human-centered AI. In this paper, we focus our analysis on scenarios consisting of a single agent operating in dynamic environments in presence of humans.

The distribution of labels given the covariates changes over time in a variety of applications of regression. Some example domains where such problems arise include economics, marketing, fashion, and supply chain optimization, where market properties evolve over time. Motivated by such problems, we revisit a model for time-varying linear regression that assumes the unknown parameters evolve according to a linear dynamical system. One way to account for distribution change in linear regression is to assume that the unknown model parameters change slowly with time [2, 15, 37]. While this assumption simplifies the problem and makes it tractable, it misses on exploiting additional structure available and it also fails to model periodicity (e.g., due to seasonality) present in some problems. As an alternative, we are interested in a dynamic model previously studied by Chow [7], Carraro [5], and Shumway et al. [26].