Intelligent assistants that follow commands or answer simple questions, such as Siri and Google search, are among the most economically important applications of AI. Future conversational AI assistants promise even greater capabilities and a better user experience through a deeper understanding of the domain, the user, or the user's purposes. But what domain and what methods are best suited to researching and realizing this promise? In this article we argue for the domain of voice document editing and for the methods of model-based reinforcement learning. The primary advantages of voice document editing are that the domain is tightly scoped and that it provides something for the conversation to be about (the document) that is delimited and fully accessible to the intelligent assistant. The advantages of reinforcement learning in general are that its methods are designed to learn from interaction without explicit instruction and that it formalizes the purposes of the assistant. Model-based reinforcement learning is needed in order to genuinely understand the domain of discourse and thereby work efficiently with the user to achieve their goals. Together, voice document editing and model-based reinforcement learning comprise a promising research direction for achieving conversational AI.

Experts in Artificial Intelligence (AI) development predict that advances in the development of intelligent systems and agents will reshape vital areas in our society. Nevertheless, if such an advance is not made prudently and critically-reflexively, it can result in negative outcomes for humanity. For this reason, several researchers in the area are trying to develop a robust, beneficial, and safe concept of AI for the preservation of humanity and the environment. Currently, several of the open problems in the field of AI research arise from the difficulty of avoiding unwanted behaviors of intelligent agents and systems, and at the same time specifying what we want such systems to do, especially when we look for the possibility of intelligent agents acting in several domains over the long term. It is of utmost importance that artificial intelligent agents have their values aligned with human values, given the fact that we cannot expect an AI to develop human moral values simply because of its intelligence, as discussed in the Orthogonality Thesis. Perhaps this difficulty comes from the way we are addressing the problem of expressing objectives, values, and ends, using representational cognitive methods. A solution to this problem would be the dynamic approach proposed by Dreyfus, whose phenomenological philosophy shows that the human experience of being-in-the-world in several aspects is not well represented by the symbolic or connectionist cognitive method, especially in regards to the question of learning values. A possible approach to this problem would be to use theoretical models such as SED (situated embodied dynamics) to address the values learning problem in AI.

Semi-supervised learning aims to learn prediction models from both labeled and unlabeled samples. There has been extensive research in this area. Among existing work, generative mixture models with Expectation-Maximization (EM) is a popular method due to clear statistical properties. However, existing literature on EM-based semi-supervised learning largely focuses on unstructured prediction, assuming that samples are independent and identically distributed. Studies on EM-based semi-supervised approach in structured prediction is limited. This paper aims to fill the gap through a comparative study between unstructured and structured methods in EM-based semi-supervised learning. Specifically, we compare their theoretical properties and find that both methods can be considered as a generalization of self-training with soft class assignment of unlabeled samples, but the structured method additionally considers structural constraint in soft class assignment. We conducted a case study on real-world flood mapping datasets to compare the two methods. Results show that structured EM is more robust to class confusion caused by noise and obstacles in features in the context of the flood mapping application.

Decision-making strategy for autonomous vehicles de-scribes a sequence of driving maneuvers to achieve a certain navigational mission. This paper utilizes the deep reinforcement learning (DRL) method to address the continuous-horizon decision-making problem on the highway. First, the vehicle kinematics and driving scenario on the freeway are introduced. The running objective of the ego automated vehicle is to execute an efficient and smooth policy without collision. Then, the particular algorithm named proximal policy optimization (PPO)-enhanced DRL is illustrated. To overcome the challenges in tardy training efficiency and sample inefficiency, this applied algorithm could realize high learning efficiency and excellent control performance. Finally, the PPO-DRL-based decision-making strategy is estimated from multiple perspectives, including the optimality, learning efficiency, and adaptability. Its potential for online application is discussed by applying it to similar driving scenarios.

This paper studies multi-agent systems that involve networks of self-interested agents. We propose a Markov Decision Process-derived framework, called RepNet-MDP, tailored to domains in which agent reputation is a key driver of the interactions between agents. The fundamentals are based on the principles of RepNet-POMDP, a framework developed by Rens et al. [11] in 2018, but addresses its mathematical inconsistencies and alleviates its intractability by only considering fully observable environments. We furthermore use an online learning algorithm for finding approximate solutions to RepNet-MDPs. In a series of experiments, RepNet agents are shown to be able to adapt their own behavior to the past behavior and reliability of the remaining agents of the network. Finally, our work identifies a limitation of the framework in its current formulation that prevents its agents from learning in circumstances in which they are not a primary actor.

Although Reinforcement Learning (RL) algorithms have found tremendous success in simulated domains, they often cannot directly be applied to physical systems, especially in cases where there are hard constraints to satisfy (e.g. on safety or resources). In standard RL, the agent is incentivized to explore any behavior as long as it maximizes rewards, but in the real world, undesired behavior can damage either the system or the agent in a way that breaks the learning process itself. In this work, we model the problem of learning with constraints as a Constrained Markov Decision Process and provide a new on-policy formulation for solving it. A key contribution of our approach is to translate cumulative cost constraints into state-based constraints. Through this, we define a safe policy improvement method which maximizes returns while ensuring that the constraints are satisfied at every step. We provide theoretical guarantees under which the agent converges while ensuring safety over the course of training. We also highlight the computational advantages of this approach. The effectiveness of our approach is demonstrated on safe navigation tasks and in safety-constrained versions of MuJoCo environments, with deep neural networks.

We explore the application of normalizing flows for improving the performance of trajectory planning for autonomous vehicles (AVs). Normalizing flows provide an invertible mapping from a known prior distribution to a potentially complex, multi-modal target distribution and allow for fast sampling with exact PDF inference. By modeling a trajectory planner's cost manifold as an energy function we learn a scene conditioned mapping from the prior to a Boltzmann distribution over the AV control space. This mapping allows for control samples and their associated energy to be generated jointly and in parallel. We propose using neural autoregressive flow (NAF) as part of an end-to-end deep learned system that allows for utilizing sensors, map, and route information to condition the flow mapping. Finally, we demonstrate the effectiveness of our approach on real world datasets over IL and hand constructed trajectory sampling techniques.

Deep Q-Learning is an important algorithm, used to solve sequential decision making problems. It involves training a Deep Neural Network, called a Deep Q-Network (DQN), to approximate a function associated with optimal decision making, the Q-function. Although wildly successful in laboratory conditions, serious gaps between theory and practice prevent its use in the real-world. In this paper, we present a comprehensive analysis of the popular and practical version of the algorithm, under realistic verifiable assumptions. An important contribution is the characterization of its performance as a function of training. To do this, we view the algorithm as an evolving dynamical system. This facilitates associating a closely-related measure process with training. Then, the long-term behavior of Deep Q-Learning is determined by the limit of the aforementioned measure process. Empirical inferences, such as the qualitative advantage of using experience replay, and performance inconsistencies even after training, are explained using our analysis. Also, our theory is general and accommodates state Markov processes with multiple stationary distributions.

A major drawback of cross-network recommender solutions is that they can only be applied to users that are overlapped across networks. Thus, the non-overlapped users, which form the majority of users are ignored. As a solution, we propose CnGAN, a novel multi-task learning based, encoder-GAN-recommender architecture. The proposed model synthetically generates source network user preferences for non-overlapped users by learning the mapping from target to source network preference manifolds. The resultant user preferences are used in a Siamese network based neural recommender architecture. Furthermore, we propose a novel user based pairwise loss function for recommendations using implicit interactions to better guide the generation process in the multi-task learning environment.We illustrate our solution by generating user preferences on the Twitter source network for recommendations on the YouTube target network. Extensive experiments show that the generated preferences can be used to improve recommendations for non-overlapped users. The resultant recommendations achieve superior performance compared to the state-of-the-art cross-network recommender solutions in terms of accuracy, novelty and diversity.

Classification problems in supervised machine learning are often troubled by the issue of imbalanced class sizes. Given binary classified data, an imbalanced stratification of the two classes will bias the predictions of a model fit to it. A model trained on data made up of 1,000 samples labeled class "0" and 100 samples labeled class "1" could naively predict class "0" for every test instance and report 90% accuracy. Such an accuracy score is deceptive, as the model is not actually "learning" any trends from the data. This can cause serious problems in deployment.