The large integration of variable energy resources is expected to shift a large part of the energy exchanges closer to real-time, where more accurate forecasts are available. In this context, the short-term electricity markets and in particular the intraday market are considered a suitable trading floor for these exchanges to occur. A key component for the successful renewable energy sources integration is the usage of energy storage. In this paper, we propose a novel modelling framework for the strategic participation of energy storage in the European continuous intraday market where exchanges occur through a centralized order book. The goal of the storage device operator is the maximization of the profits received over the entire trading horizon, while taking into account the operational constraints of the unit. The sequential decision-making problem of trading in the intraday market is modelled as a Markov Decision Process. An asynchronous distributed version of the fitted Q iteration algorithm is chosen for solving this problem due to its sample efficiency. The large and variable number of the existing orders in the order book motivates the use of high-level actions and an alternative state representation. Historical data are used for the generation of a large number of artificial trajectories in order to address exploration issues during the learning process. The resulting policy is back-tested and compared against a benchmark strategy that is the current industrial standard. Results indicate that the agent converges to a policy that achieves in average higher total revenues than the benchmark strategy.

This work presents a modular and hierarchical approach to learn policies for exploring 3D environments, called `Active Neural SLAM'. Our approach leverages the strengths of both classical and learning-based methods, by using analytical path planners with learned SLAM module, and global and local policies. The use of learning provides flexibility with respect to input modalities (in the SLAM module), leverages structural regularities of the world (in global policies), and provides robustness to errors in state estimation (in local policies). Such use of learning within each module retains its benefits, while at the same time, hierarchical decomposition and modular training allow us to sidestep the high sample complexities associated with training end-to-end policies. Our experiments in visually and physically realistic simulated 3D environments demonstrate the effectiveness of our approach over past learning and geometry-based approaches. The proposed model can also be easily transferred to the PointGoal task and was the winning entry of the CVPR 2019 Habitat PointGoal Navigation Challenge.

Reinforcement learning is nowadays a popular framework for solving different decision making problems in automated driving. However, there are still some remaining crucial challenges that need to be addressed for providing more reliable policies. In this paper, we propose a generic risk-aware DQN approach in order to learn high level actions for driving through unsignalized occluded intersections. The proposed state representation provides lane based information which allows to be used for multi-lane scenarios. Moreover, we propose a risk based reward function which punishes risky situations instead of only collision failures. Such rewarding approach helps to incorporate risk prediction into our deep Q network and learn more reliable policies which are safer in challenging situations. The efficiency of the proposed approach is compared with a DQN learned with conventional collision based rewarding scheme and also with a rule-based intersection navigation policy. Evaluation results show that the proposed approach outperforms both of these methods. It provides safer actions than collision-aware DQN approach and is less overcautious than the rule-based policy.

Location is key to spatialize internet-of-things (IoT) data. However, it is challenging to use low-cost IoT devices for robust unsupervised localization (i.e., localization without training data that have known location labels). Thus, this paper proposes a deep reinforcement learning (DRL) based unsupervised wireless-localization method. The main contributions are as follows. (1) This paper proposes an approach to model a continuous wireless-localization process as a Markov decision process (MDP) and process it within a DRL framework. (2) To alleviate the challenge of obtaining rewards when using unlabeled data (e.g., daily-life crowdsourced data), this paper presents a reward-setting mechanism, which extracts robust landmark data from unlabeled wireless received signal strengths (RSS). (3) To ease requirements for model re-training when using DRL for localization, this paper uses RSS measurements together with agent location to construct DRL inputs. The proposed method was tested by using field testing data from multiple Bluetooth 5 smart ear tags in a pasture. Meanwhile, the experimental verification process reflected the advantages and challenges for using DRL in wireless localization.

Large random graphs have been very popular in the last decade since they are powerful tools to model complex phenomena like interactions on social networks or the spread of a disease. In practical cases, detecting communities of well connected nodes in a graph is a major issue, motivating the study of the Stochastic Block Model (SBM). In this model, each node belongs to a particular community and edges are sampled independently according to a probability depending of the communities of the nodes. Aiming at progressively bridging the gap between models and reality, time evolving random graphs have been recently introduced. In [20], a Stochastic Block Temporal Model is considered where the temporal evolution is modeled through a discrete hidden Markov chain on the nodes membership and where the connection probabilities also evolve through time.

We present a unified statistical framework for characterizing community structure of brain functional networks that captures variation across individuals and evolution over time. Existing methods for community detection focus only on single-subject analysis of dynamic networks; while recent extensions to multiple-subjects analysis are limited to static networks. To overcome these limitations, we propose a multi-subject, Markov-switching stochastic block model (MSS-SBM) to identify state-related changes in brain community organization over a group of individuals. We first formulate a multilayer extension of SBM to describe the time-dependent, multi-subject brain networks. We develop a novel procedure for fitting the multilayer SBM that builds on multislice modularity maximization which can uncover a common community partition of all layers (subjects) simultaneously. By augmenting with a dynamic Markov switching process, our proposed method is able to capture a set of distinct, recurring temporal states with respect to inter-community interactions over subjects and the change points between them. Simulation shows accurate community recovery and tracking of dynamic community regimes over multilayer networks by the MSS-SBM. Application to task fMRI reveals meaningful non-assortative brain community motifs, e.g., core-periphery structure at the group level, that are associated with language comprehension and motor functions suggesting their putative role in complex information integration. Our approach detected dynamic reconfiguration of modular connectivity elicited by varying task demands and identified unique profiles of intra and inter-community connectivity across different task conditions. The proposed multilayer network representation provides a principled way of detecting synchronous, dynamic modularity in brain networks across subjects.

We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable in this setting. Our key technical contribution is an adversarial objective that can be used to tractably estimate mutual information assuming only the feasibility of cross entropy calculation. We develop a concrete realization of this general formulation with Markov distributions over binary encodings. We report critical and unexpected findings on practical aspects of the objective such as the choice of variational priors. We apply our model on document hashing and show that it outperforms current best baselines based on discrete and vector quantized variational autoencoders. It also yields highly compressed interpretable representations.

We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by "controlled" Markov noise. In particular, the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic behavior of our framework by relating it to limiting differential inclusions in both time scales that are defined in terms of the ergodic occupation measures associated with the controlled Markov processes. Using a special case of our results, we present a solution to the off-policy convergence problem for temporal-difference learning with linear function approximation. We compile several aspects of the dynamics of stochastic approximation algorithms with Markov iterate-dependent noise when the iterates are not known to be stable beforehand. We achieve the same by extending the lock-in probability (i.e. the probability of convergence to a specific attractor of the limiting o.d.e. given that the iterates are in its domain of attraction after a sufficiently large number of iterations (say) n_0) framework to such recursions. We use these results to prove almost sure convergence of the iterates to the specified attractor when the iterates satisfy an "asymptotic tightness" condition. This, in turn, is shown to be useful in analyzing the tracking ability of general "adaptive" algorithms. Finally, we obtain the first informative error bounds on function approximation for the policy evaluation algorithm proposed by Basu et al. when the aim is to find the risk-sensitive cost represented using exponential utility. We show that this happens due to the absence of difference term in the earlier bound which is always present in all our bounds when the state space is large.

Reinforcement-based training methods have emerged as the most popular choice to train an efficient and effective dialog policy. However, these methods are suffering from sparse and unstable reward signals usually returned from the user simulator at the end of the dialog. Besides, the reward signal is manually designed by human experts which requires domain knowledge. A number of adversarial learning methods have been proposed to learn the reward function together with the dialog policy. However, to alternatively update the dialog policy and the reward model on the fly, the algorithms to update the dialog policy are limited to policy gradient-based algorithms, such as REINFORCE and PPO. Besides, the alternative training of the dialog agent and the reward model can easily get stuck in local optimum or result in mode collapse. In this work, we propose to decompose the previous adversarial training into two different steps. We first train the discriminator with an auxiliary dialog generator and then incorporate this trained reward model to a common reinforcement learning method to train a high-quality dialog agent. This approach is applicable to both on-policy and off-policy reinforcement learning methods. By conducting several experiments, we show the proposed methods can achieve remarkable task success and its potential to transfer knowledge from existing domains to a new domain.

Music Generation (MG) is an interesting research topic that links the art of music and Artificial Intelligence (AI). The goal is to train an artificial composer to generate infinite, fresh, and pleasurable musical pieces. Music has different parts such as melody, harmony, and rhythm. In this paper, we propose a Generative Genetic Algorithm (GGA) to produce a melody automatically. The main GGA uses a Long Short-Term Memory (LSTM) recurrent neural network as the objective function, which should be trained by a spectrum of bad-to-good melodies. These melodies have to be provided by another GGA with a different objective function. Good melodies have been provided by CAMPINs collection. We have considered the rhythm in this work, too. The experimental results clearly show that the proposed GGA method is able to generate eligible melodies with natural transitions and without rhythm error.