Gaussian processes (GPs) are nonparametric Bayesian models that have been applied to regression and classification problems. One of the approaches to alleviate their cubic training cost is the use of local GP experts trained on subsets of the data. In particular, product-of-expert models combine the predictive distributions of local experts through a tractable product operation. While these expert models allow for massively distributed computation, their predictions typically suffer from erratic behaviour of the mean or uncalibrated uncertainty quantification. By calibrating predictions via a tempered softmax weighting, we provide a solution to these problems for multiple product-of-expert models, including the generalised product of experts and the robust Bayesian committee machine. Furthermore, we leverage the optimal transport literature and propose a new product-of-expert model that combines predictions of local experts by computing their Wasserstein barycenter, which can be applied to both regression and classification.

Training deep reinforcement learning agents on environments with multiple levels / scenes from the same task, has become essential for many applications aiming to achieve generalization and domain transfer from simulation to the real world. While such a strategy is helpful with generalization, the use of multiple scenes significantly increases the variance of samples collected for policy gradient computations. Current methods, effectively continue to view this collection of scenes as a single Markov decision process (MDP), and thus learn a scene-generic value function V(s). However, we argue that the sample variance for a multi-scene environment is best minimized by treating each scene as a distinct MDP, and then learning a joint value function V(s,M) dependent on both state s and MDP M. We further demonstrate that the true joint value function for a multi-scene environment, follows a multi-modal distribution which is not captured by traditional CNN / LSTM based critic networks. To this end, we propose a dynamic value estimation (DVE) technique, which approximates the true joint value function through a sparse attention mechanism over multiple value function hypothesis / modes. The resulting agent not only shows significant improvements in the final reward score across a range of OpenAI ProcGen environments, but also exhibits enhanced navigation efficiency and provides an implicit mechanism for unsupervised state-space skill decomposition.

The number of connected smart devices has been increasing exponentially for different Internet-of-Things (IoT) applications. Security has been a long run challenge in the IoT systems which has many attack vectors, security flaws and vulnerabilities. Securing billions of B connected devices in IoT is a must task to realize the full potential of IoT applications. Recently, researchers have proposed many security solutions for IoT. Machine learning has been proposed as one of the emerging solutions for IoT security and Reinforcement learning is gaining more popularity for securing IoT systems. Reinforcement learning, unlike other machine learning techniques, can learn the environment by having minimum information about the parameters to be learned. It solves the optimization problem by interacting with the environment adapting the parameters on the fly. In this paper, we present an comprehensive survey of different types of cyber-attacks against different IoT systems and then we present reinforcement learning and deep reinforcement learning based security solutions to combat those different types of attacks in different IoT systems. Furthermore, we present the Reinforcement learning for securing CPS systems (i.e., IoT with feedback and control) such as smart grid and smart transportation system. The recent important attacks and countermeasures using reinforcement learning B in IoT are also summarized in the form of tables. With this paper, readers can have a more thorough understanding of IoT security attacks and countermeasures using Reinforcement Learning, as well as research trends in this area.

As the potential applications of Artificial Intelligence (AI) in the financial sector increases, ethical issues become gradually latent. The distrust of individuals, social groups, and governments about the risks arising from Fintech's activities is growing. Due to this scenario, the preparation of recommendations and Ethics Guidelines is increasing and the risks of being chosen the principles and ethical values most appropriate to companies are high. Thus, this exploratory research aims to analyze the benefits of the application of the stakeholder theory and the idea of Social License to build an environment of trust and for the realization of ethical principles by Fintech. The formation of a Fintech association for the creation of a Social License will allow early-stage Fintech to participate from the beginning of its activities in the elaboration of a dynamic ethical code and with the participation of stakeholders.

Fairness has emerged as an important concern in automated decision-making in recent years, especially when these decisions affect human welfare. In this work, we study fairness in temporally extended decision-making settings, specifically those formulated as Markov Decision Processes (MDPs). Our proposed notion of fairness ensures that each state's long-term visitation frequency is more than a specified fraction. In an average-reward MDP (AMDP) setting, we formulate the problem as a bilinear saddle point program and, for a generative model, solve it using a Stochastic Mirror Descent (SMD) based algorithm. The proposed solution guarantees a simultaneous approximation on the expected average-reward and the long-term state-visitation frequency. We validate our theoretical results with experiments on synthetic data.

We consider a decision maker who must choose an action in order to maximize a reward function that depends also on an unknown parameter {\Theta}. The decision maker can delay taking the action in order to experiment and gather additional information on {\Theta}. We model the decision maker's problem using a Bayesian sequential experimentation framework and use dynamic programming and diffusion-asymptotic analysis to solve it. For that, we scale our problem in a way that both the average number of experiments that is conducted per unit of time is large and the informativeness of each individual experiment is low. Under such regime, we derive a diffusion approximation for the sequential experimentation problem, which provides a number of important insights about the nature of the problem and its solution. Our solution method also shows that the complexity of the problem grows only quadratically with the cardinality of the set of actions from which the decision maker can choose. We illustrate our methodology and results using a concrete application in the context of assortment selection and new product introduction. Specifically, we study the problem of a seller who wants to select an optimal assortment of products to launch into the marketplace and is uncertain about consumers' preferences. Motivated by emerging practices in e-commerce, we assume that the seller is able to use a crowdvoting system to learn these preferences before a final assortment decision is made. In this context, we undertake an extensive numerical analysis to assess the value of learning and demonstrate the effectiveness and robustness of the heuristics derived from the diffusion approximation.

In Apprenticeship Learning (AL), we are given a Markov Decision Process (MDP) without access to the cost function. Instead, we observe trajectories sampled by an expert that acts according to some policy. The goal is to find a policy that matches the expert's performance on some predefined set of cost functions. We introduce an online variant of AL (Online Apprenticeship Learning; OAL), where the agent is expected to perform comparably to the expert while interacting with the environment. We show that the OAL problem can be effectively solved by combining two mirror descent based no-regret algorithms: one for policy optimization and another for learning the worst case cost. To this end, we derive a convergent algorithm with $O(\sqrt{K})$ regret, where $K$ is the number of interactions with the MDP, and an additional linear error term that depends on the amount of expert trajectories available. Importantly, our algorithm avoids the need to solve an MDP at each iteration, making it more practical compared to prior AL methods. Finally, we implement a deep variant of our algorithm which shares some similarities to GAIL \cite{ho2016generative}, but where the discriminator is replaced with the costs learned by the OAL problem. Our simulations demonstrate our theoretically grounded approach outperforms the baselines.

Agents operating in unstructured environments often produce negative side effects (NSE), which are difficult to identify at design time. While the agent can learn to mitigate the side effects from human feedback, such feedback is often expensive and the rate of learning is sensitive to the agent's state representation. We examine how humans can assist an agent, beyond providing feedback, and exploit their broader scope of knowledge to mitigate the impacts of NSE. We formulate this problem as a human-agent team with decoupled objectives. The agent optimizes its assigned task, during which its actions may produce NSE. The human shapes the environment through minor reconfiguration actions so as to mitigate the impacts of the agent's side effects, without affecting the agent's ability to complete its assigned task. We present an algorithm to solve this problem and analyze its theoretical properties. Through experiments with human subjects, we assess the willingness of users to perform minor environment modifications to mitigate the impacts of NSE. Empirical evaluation of our approach shows that the proposed framework can successfully mitigate NSE, without affecting the agent's ability to complete its assigned task.

In a Bayesian neural network (BNN), we specify a prior p(w) over the neural network parameters, and compute the posterior distribution over parameters conditioned on training data, p(w x, y) p(y w, x)p(w)/p(y x). This procedure should give considerable advantages for reasoning about predictive uncertainty, which is especially relevant in the small-data setting. Crucially, to perform Bayesian inference, we need to choose a prior that accurately reflects our beliefs about the parameters before seeing any data (Bayes, 1763; Gelman et al., 2013). However, the most common choice of the prior for BNN weights is the simplest one: the isotropic Gaussian. Isotropic Gaussians are used across almost all fields of Bayesian deep learning, ranging from variational inference (Blundell et al., 2015; Dusenberry et al., 2020), to sampling-based inference (Zhang et al., 2019), and even to infinite networks (Lee et al., 2017; Garriga-Alonso et al., 2019). This is troubling, since isotropic Gaussian priors are almost certainly not the best choice. Indeed, despite the progress on more accurate and efficient inference procedures, in most settings, the posterior predictive of BNNs using a Gaussian prior still leads to worse predictive performance than a baseline obtained by training the network with standard stochastic gradient descent (SGD) (e.g., Zhang et al., 2019; Heek & Kalchbrenner, 2019; Wenzel et al., 2020a). However, it has been shown that the performance of BNNs can be improved by artificially reducing posterior uncertainty using "cold posteriors" (Wenzel et al., 2020a).

Q-learning, which seeks to learn the optimal Q-function of a Markov decision process (MDP) in a model-free fashion, lies at the heart of reinforcement learning. When it comes to the synchronous setting (such that independent samples for all state-action pairs are drawn from a generative model in each iteration), substantial progress has been made recently towards understanding the sample efficiency of Q-learning. To yield an entrywise $\varepsilon$-accurate estimate of the optimal Q-function, state-of-the-art theory requires at least an order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^5\varepsilon^{2}}$ samples for a $\gamma$-discounted infinite-horizon MDP with state space $\mathcal{S}$ and action space $\mathcal{A}$. In this work, we sharpen the sample complexity of synchronous Q-learning to an order of $\frac{|\mathcal{S}||\mathcal{A}|}{(1-\gamma)^4\varepsilon^2}$ (up to some logarithmic factor) for any $0<\varepsilon <1$, leading to an order-wise improvement in terms of the effective horizon $\frac{1}{1-\gamma}$. Analogous results are derived for finite-horizon MDPs as well. Our finding unveils the effectiveness of vanilla Q-learning, which matches that of speedy Q-learning without requiring extra computation and storage. A key ingredient of our analysis lies in the establishment of novel error decompositions and recursions, which might shed light on how to analyze finite-sample performance of other Q-learning variants.