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.

Many Reinforcement Learning (RL) approaches use joint control signals (positions, velocities, torques) as action space for continuous control tasks. We propose to lift the action space to a higher level in the form of subgoals for a motion generator (a combination of motion planner and trajectory executor). We argue that, by lifting the action space and by leveraging sampling-based motion planners, we can efficiently use RL to solve complex, long-horizon tasks that could not be solved with existing RL methods in the original action space. We propose ReLMoGen -- a framework that combines a learned policy to predict subgoals and a motion generator to plan and execute the motion needed to reach these subgoals. To validate our method, we apply ReLMoGen to two types of tasks: 1) Interactive Navigation tasks, navigation problems where interactions with the environment are required to reach the destination, and 2) Mobile Manipulation tasks, manipulation tasks that require moving the robot base. These problems are challenging because they are usually long-horizon, hard to explore during training, and comprise alternating phases of navigation and interaction. Our method is benchmarked on a diverse set of seven robotics tasks in photo-realistic simulation environments. In all settings, ReLMoGen outperforms state-of-the-art Reinforcement Learning and Hierarchical Reinforcement Learning baselines. ReLMoGen also shows outstanding transferability between different motion generators at test time, indicating a great potential to transfer to real robots.

As the operations of autonomous systems generally affect simultaneously several users, it is crucial that their designs account for fairness considerations. In contrast to standard (deep) reinforcement learning (RL), we investigate the problem of learning a policy that treats its users equitably. In this paper, we formulate this novel RL problem, in which an objective function, which encodes a notion of fairness that we formally define, is optimized. For this problem, we provide a theoretical discussion where we examine the case of discounted rewards and that of average rewards. During this analysis, we notably derive a new result in the standard RL setting, which is of independent interest: it states a novel bound on the approximation error with respect to the optimal average reward of that of a policy optimal for the discounted reward. Since learning with discounted rewards is generally easier, this discussion further justifies finding a fair policy for the average reward by learning a fair policy for the discounted reward. Thus, we describe how several classic deep RL algorithms can be adapted to our fair optimization problem, and we validate our approach with extensive experiments in three different domains.

This primer explores the exciting subject of intelligence. Intelligence is a fundamental component of all living things, as well as Artificial Intelligence(AI). Artificial Intelligence has the potential to affect all of our lives and a new era for modern humans. This paper is an attempt to explore the ideas associated with intelligence, and by doing so understand the implications, constraints, and potentially the capabilities of future Artificial Intelligence. As an exploration, we journey into different parts of intelligence that appear essential. We hope that people find this useful in determining where Artificial Intelligence may be headed. Also, during the exploration, we hope to create new thought-provoking questions. Intelligence is not a single weighable quantity but a subject that spans Biology, Physics, Philosophy, Cognitive Science, Neuroscience, Psychology, and Computer Science. Historian Yuval Noah Harari pointed out that engineers and scientists in the future will have to broaden their understandings to include disciplines such as Psychology, Philosophy, and Ethics. Fiction writers have long portrayed engineers and scientists as deficient in these areas. Today, modern society, the emergence of Artificial Intelligence, and legal requirements all act as forcing functions to push these broader subjects into the foreground. We start with an introduction to intelligence and move quickly onto more profound thoughts and ideas. We call this a Life, the Universe and Everything primer, after the famous science fiction book by Douglas Adams. Forty-two may very well be the right answer, but what are the questions?

Current research directions in deep reinforcement learning include bridging the simulation-reality gap, improving sample efficiency of experiences in distributed multi-agent reinforcement learning, together with the development of robust methods against adversarial agents in distributed learning, among many others. In this work, we are particularly interested in analyzing how multi-agent reinforcement learning can bridge the gap to reality in distributed multi-robot systems where the operation of the different robots is not necessarily homogeneous. These variations can happen due to sensing mismatches, inherent errors in terms of calibration of the mechanical joints, or simple differences in accuracy. While our results are simulation-based, we introduce the effect of sensing, calibration, and accuracy mismatches in distributed reinforcement learning with proximal policy optimization (PPO). We discuss on how both the different types of perturbances and how the number of agents experiencing those perturbances affect the collaborative learning effort. The simulations are carried out using a Kuka arm model in the Bullet physics engine. This is, to the best of our knowledge, the first work exploring the limitations of PPO in multi-robot systems when considering that different robots might be exposed to different environments where their sensors or actuators have induced errors. With the conclusions of this work, we set the initial point for future work on designing and developing methods to achieve robust reinforcement learning on the presence of real-world perturbances that might differ within a multi-robot system.