During the past decade, Artificial Intelligence (AI), and by extension Machine Learning (ML), have seen an unprecedented rise in both industry and research. The progressive improvement of computer hardware associated with the need to process larger and larger amounts of data made these underestimated techniques shine under a new light. Reinforcement Learning (RL) focuses on learning how to map situations to actions, in order to maximize a numerical reward signal [102]. The learner is not told which actions to take, but instead must discover which actions are the most rewarding by trying them. Reinforcement learning addresses the problem of how agents should learn a policy that take actions to maximize the cumulative reward through interaction with the environment [31]. Recent progress in Deep Learning (DL) for learning feature representations has significantly impacted RL, and the combination of both methods (known as deep RL) has led to remarkable results in a lot of areas. Typically, RL is used to solve optimisation problems when the system has a very large number of states and has a complex stochastic structure. Notable examples include training agents to play Atari games based on raw pixels [75, 76], board games [96, 97], complex real-world robotics problems such as manipulation [8] or grasping [54] and other real-world applications such as resource management in computer clusters [72], network traffic signal control [9], chemical reactions optimization [117] or recommendation systems [116].

Imitation learning algorithms have been interpreted as variants of divergence minimization problems. The ability to compare occupancy measures between experts and learners is crucial in their effectiveness in learning from demonstrations. In this paper, we present tractable solutions by formulating imitation learning as minimization of the Sinkhorn distance between occupancy measures. The formulation combines the valuable properties of optimal transport metrics in comparing non-overlapping distributions with a cosine distance cost defined in an adversarially learned feature space. This leads to a highly discriminative critic network and optimal transport plan that subsequently guide imitation learning. We evaluate the proposed approach using both the reward metric and the Sinkhorn distance metric on a number of MuJoCo experiments.

Ensemble models are powerful model building tools that are developed with a focus to improve the accuracy of model predictions. They find applications in time series forecasting in varied scenarios including but not limited to process industries, health care, and economics where a single model might not provide optimal performance. It is known that if models selected for data modelling are distinct (linear/non-linear, static/dynamic) and independent (minimally correlated models), the accuracy of the predictions is improved. Various approaches suggested in the literature to weigh the ensemble models use a static set of weights. Due to this limitation, approaches using a static set of weights for weighing ensemble models cannot capture the dynamic changes or local features of the data effectively. To address this issue, a Reinforcement Learning (RL) approach to dynamically assign and update weights of each of the models at different time instants depending on the nature of data and the individual model predictions is proposed in this work. The RL method implemented online, essentially learns to update the weights and reduce the errors as the time progresses. Simulation studies on time series data showed that the dynamic weighted approach using RL learns the weight better than existing approaches. The accuracy of the proposed method is compared with an existing approach of online Neural Network tuning quantitatively through normalized mean square error(NMSE) values.

A large amount of wastewater has been produced nowadays. Wastewater treatment plants (WWTPs) are designed to eliminate pollutants and alleviate environmental pollution resulting from human activities. However, the construction and operation of WWTPs still have negative impacts. WWTPs are complex to control and optimize because of high nonlinearity and variation. This study used a novel technique, multi-agent deep reinforcement learning (DRL), to optimize dissolved oxygen (DO) and dosage in a hypothetical WWTP. The reward function is specially designed as LCA-based form to achieve sustainability optimization. Four scenarios: baseline, LCA-oriented, cost-oriented and effluent-oriented are considered. The result shows that optimization based on LCA has lowest environmental impacts. The comparison of different SRT indicates that a proper SRT can reduce negative impacts greatly. It is worth mentioning that the retrofitting of WWTPs should be implemented with the consideration of other environmental impacts except cost. Moreover, the comparison between DRL and genetic algorithm (GA) indicates that DRL can solve optimization problems effectively and has great extendibility. In a nutshell, there are still limits and shortcomings of this work, future studies are required.

Storage systems for cloud computing merge a large number of commodity computers into a single large storage pool. It provides high-performance storage over an unreliable, and dynamic network at a lower cost than purchasing and maintaining large mainframe. In this paper, we examine whether it is feasible to apply Reinforcement Learning(RL) to system domain problems. Our experiments show that the RL model is comparable, even outperform other heuristics for block management problem. However, our experiments are limited in terms of scalability and fidelity. Even though our formulation is not very practical,applying Reinforcement Learning to system domain could offer good alternatives to existing heuristics.

This paper investigates the use of Reinforcement Learning for the robust design of low-thrust interplanetary trajectories in presence of severe disturbances, modeled alternatively as Gaussian additive process noise, observation noise, control actuation errors on thrust magnitude and direction, and possibly multiple missed thrust events. The optimal control problem is recast as a time-discrete Markov Decision Process to comply with the standard formulation of reinforcement learning. An open-source implementation of the state-of-the-art algorithm Proximal Policy Optimization is adopted to carry out the training process of a deep neural network, used to map the spacecraft (observed) states to the optimal control policy. The resulting Guidance and Control Network provides both a robust nominal trajectory and the associated closed-loop guidance law. Numerical results are presented for a typical Earth-Mars mission. First, in order to validate the proposed approach, the solution found in a (deterministic) unperturbed scenario is compared with the optimal one provided by an indirect technique. Then, the robustness and optimality of the obtained closed-loop guidance laws is assessed by means of Monte Carlo campaigns performed in the considered uncertain scenarios.

This paper investigates the optimal control problem for a class of discrete-time stochastic systems subject to additive and multiplicative noises. A stochastic Lyapunov equation and a stochastic algebra Riccati equation are established for the existence of the optimal admissible control policy. A model-free reinforcement learning algorithm is proposed to learn the optimal admissible control policy using the data of the system states and inputs without requiring any knowledge of the system matrices. It is proven that the learning algorithm converges to the optimal admissible control policy. The implementation of the model-free algorithm is based on batch least squares and numerical average. The proposed algorithm is illustrated through a numerical example, which shows our algorithm outperforms other policy iteration algorithms.

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected, static datasets without further interaction. However, in practice, offline RL presents a major challenge, and standard off-policy RL methods can fail due to overestimation of values induced by the distributional shift between the dataset and the learned policy, especially when training on complex and multi-modal data distributions. In this paper, we propose conservative Q-learning (CQL), which aims to address these limitations by learning a conservative Q-function such that the expected value of a policy under this Q-function lower-bounds its true value. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a policy learning procedure with theoretical improvement guarantees. In practice, CQL augments the standard Bellman error objective with a simple Q-value regularizer which is straightforward to implement on top of existing deep Q-learning and actor-critic implementations. On both discrete and continuous control domains, we show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return, especially when learning from complex and multi-modal data distributions.

This article introduces an open framework, called VSSS-RL, for studying Reinforcement Learning (RL) and sim-to-real in robot soccer, focusing on the IEEE Very Small Size Soccer (VSSS) league. We propose a simulated environment in which continuous or discrete control policies can be trained to control the complete behavior of soccer agents and a sim-to-real method based on domain adaptation to adapt the obtained policies to real robots. Our results show that the trained policies learned a broad repertoire of behaviors that are difficult to implement with handcrafted control policies. With VSSS-RL, we were able to beat human-designed policies in the 2019 Latin American Robotics Competition (LARC), achieving 4th place out of 21 teams, being the first to apply Reinforcement Learning (RL) successfully in this competition. Both environment and hardware specifications are available open-source to allow reproducibility of our results and further studies.

Autonomous car racing raises fundamental robotics challenges such as planning minimum-time trajectories under uncertain dynamics and controlling the car at its friction limits. In this project, we consider the task of autonomous car racing in the top-selling car racing game Gran Turismo Sport. Gran Turismo Sport is known for its detailed physics simulation of various cars and tracks. Our approach makes use of maximum-entropy deep reinforcement learning and a new reward design to train a sensorimotor policy to complete a given race track as fast as possible. We evaluate our approach in three different time trial settings with different cars and tracks. Our results show that the obtained controllers not only beat the built-in non-player character of Gran Turismo Sport, but also outperform the fastest known times in a dataset of personal best lap times of over 50,000 human drivers.