A deep recurrent Q network towards self‐adapting distributed microservice architecture

In 5G, eMBB services are defined to support high data rate, while URLLC services focus on low latency and high reliability. Multiplexing these two services on the same wireless radio frequency leads to a challenging radio resource allocation problem due to their heterogeneous requirements. In this paper, we formulate this problem as two non-linear programming non-convex optimization subproblems, aiming to maximize the average data rate of all eMBB services while satisfying the delay constraint of each URLLC service. We propose an event-driven deep reinforcement learning (DRL) based resource allocation mechanism (EDRL-RAM), which includes two schedulers: eMBB scheduler and URLLC scheduler to achieve long-term optimization of eMBB and URLLC performance. The eMBB scheduler will intelligently allocate resource for each incoming eMBB event, and the URLLC scheduler will intelligently distribute the incoming URLLC event during the ongoing transmissions of eMBB services. The proposed EDRL-RAM makes full use of four different DRL techniques to deal with stochastic event arrivals and network conditions, namely Policy Gradient (PG), Deep Q-learning Network (DQN), Advantage Actor Critic (A2C), and Deep Deterministic Policy Gradient (DDPG), in both eMBB and URLLC schedulers. The simulation results show that in our proposed EDRL-RAM, the order of data rate and delay performance is DDPG, A2C, DQN, and PG. The data rate and delay performance of the proposed EDRL-RAM utilizing any of the four DRL techniques are better than SAFE-TS, which is the best available related work.

The problem of adaptive human-machine interaction is investigated. It is sought that not only the human learns how to perform a task with a novel machine, but the machine itself co-adapts to the human style in the interaction. This requires solving the problem of two agents co-adapting or co-learning at the same time. Due to the lack of human learning and performance models, it is hypothesized that reinforcement learning with policy gradient algorithms are good candidates for addressing this problem with robustness and fast convergence.

Dynamic energy dispatch strategy for integrated energy system based on improved deep reinforcement learning

Lexicographic multi-objective problems, which consist of multiple conflicting subtasks with explicit priorities, are common in real-world applications. Despite the advantages of Reinforcement Learning (RL) in single tasks, extending conventional RL methods to prioritized multiple objectives remains challenging. In particular, traditional Safe RL and Multi-Objective RL (MORL) methods have difficulty enforcing priority orderings efficiently. Therefore, Lexicographic Multi-Objective RL (LMORL) methods have been developed to address these challenges. However, existing LMORL methods either rely on heuristic threshold tuning with prior knowledge or are restricted to discrete domains. To overcome these limitations, we propose Lexicographically Projected Policy Gradient RL (LPPG-RL), a novel LMORL framework which leverages sequential gradient projections to identify feasible policy update directions, thereby enabling LPPG-RL broadly compatible with all policy gradient algorithms in continuous spaces. LPPG-RL reformulates the projection step as an optimization problem, and utilizes Dykstra's projection rather than generic solvers to deliver great speedups, especially for small- to medium-scale instances. In addition, LPPG-RL introduces Subproblem Exploration (SE) to prevent gradient vanishing, accelerate convergence and enhance stability. We provide theoretical guarantees for convergence and establish a lower bound on policy improvement. Finally, through extensive experiments in a 2D navigation environment, we demonstrate the effectiveness of LPPG-RL, showing that it outperforms existing state-of-the-art continuous LMORL methods.

A large class of sequential decision-making problems under uncertainty, with broad applications from preventive maintenance to event-triggered control can be modeled in the framework of semi-Markov decision processes (SMDPs). Unlike Markov decision processes (MDPs), SMDPs are underexplored in the online and reinforcement learning (RL) settings. In this paper, we extend the well-known deterministic policy gradient (DPG) theorem in MDPs to SMDPs under average-reward criterion. The existing stochastic policy gradient methods not only require, in general, a large number of samples for training, but they also suffer from high variance in the gradient estimation when applied to problems with deterministic optimal policy. Our DPG method can potentially remedy these issues. On the basis of this method and depending on the choice of a critic, different actor–critic algorithms can easily be developed in the RL setup. We present two example actor–critic algorithms. Both algorithms employ our developed policy gradient theorem for their actors, but use two different critics; one uses a simple SARSA update while the other one uses the same on-policy update but with compatible function approximators. We demonstrate the efficacy of our method both mathematically and via simulations.

The variability of renewable energy within microgrids (MGs) necessitates the smoothing of power fluctuations through the effective scheduling of internal power equipment. Otherwise, significant power variations on the tie‐line connecting the MG to the main power grid could occur. This study introduces an innovative scheduling strategy that utilizes a data‐driven approach, employing a deep reinforcement learning algorithm to achieve this smoothing effect. The strategy prioritizes the scheduling of MG's internal power devices, taking into account the stochastic charging patterns of electric vehicles. The scheduling optimization model is initially described as a Markov decision process with the goal of minimizing power fluctuations on the interconnection lines and operational costs of the MG. Subsequently, after preprocessing the historical operational data of the MG, an enhanced scheduling strategy is developed through a neural network learning process. Finally, the results from four scheduling scenarios demonstrate the significant impact of the proposed strategy. Comparisons of reward curves before and after data preprocessing underscore its importance. In contrast to optimization results from deep deterministic policy gradient, soft actor‐critic, and particle swarm optimization algorithms, the superiority of the deep deterministic policy gradient algorithm with the addition of a priority experience replay mechanism is highlighted.

In this paper, we develop a reinforcement learning-based scheme for the real-time energy management of a smart home that contains a photovoltaic-energy storage system. The objective of the proposed scheme is to minimize the electricity supplying cost by appropriately scheduling the storage system on a daily basis. The problem is formulated as a Markov decision process, which is optimized using the Deep Deterministic Policy Gradient (DDPG) algorithm. The main advantage of our proposed method compared to optimization-based ones is the ability to obtain effective daily schedules without relying on stochastic variables’ forecasts. In addition, nonlinearities related to the system’s operation can be effectively modeled, without the necessity of approximating them, as in linear optimization-based methods. The results confirm the ability of the DDPG agent to learn from historical data, and then to generalize the obtained knowledge to deal with real-time situations.

Introduction Reinforcement learning formalizes the concept of learning from interactions.1 Broadly, reinforcement learning focuses on a setting in which an agent (decision maker) sequentially interacts with an environment that is partially unknown to them. At each stage, the agent takes an action and receives a reward. The objective of the agent is to maximize rewards accumulated in the long run. There are many situations in health care where decisions are made sequentially for which reinforcement learning approaches could prove useful for decision making. Throughout this article, we consider treatment prescription as an archetypical example to connect reinforcement learning concepts to a health care setting. In this setting, the care provider, the prescribed treatment, and the patients can be viewed as the agent, the action, and the environment, respectively, as depicted in Figure 1.Figure 1: Sequential treatment of AKI or CKD complications modeled as a reinforcement learning problem.Background In this section, with the objective of making reinforcement learning literature more accessible to a clinical audience, we briefly introduce related fundamental concepts and approaches. We refer the interested reader to Sutton and Barto1 for a comprehensive introduction to reinforcement learning. Markov Decision Processes Markov decision processes (MDPs) are a formalism of the sequential decision-making problem that has been central to the theoretical and practical advancements of reinforcement learning. In each stage of an MDP, the agent observes the state of the environment and takes an action, which, in turn, results in a change of the state. This change of state is assumed to be probabilistic with the next state being determined only by the preceding state, the chosen action, and the transition probability. The agent also receives a reward that is a function of the taken action, the preceding state, and the subsequent state. In an MDP, the objective of the agent is to maximize the return defined as the reward accumulated over a time horizon. In some applications, it is common to consider the horizon to be infinite, in which case the future rewards are discounted by a factor smaller than one. The selection of action by the agent on the basis of the observed state is known as the policy. More formally, a policy is a probabilistic mapping from states to each possible action. Because the policy and the reward are a function of the state, it is critical to estimate the utility of being in a certain state. More specifically, the value function is defined as the expected return starting from a given state under the chosen policy. Under this formalism, the objective of the agent is to find the optimal policy that maximizes the value function for all states. Reinforcement Learning Methods Action-value methods are a class of reinforcement learning methods in which the actions are chosen on the basis of the estimation of their long-term value. A prominent example of an action-value method is Q-learning in which the agent iteratively takes actions with the highest estimated values and updates the action-state value function on the basis of new observations. Policy gradient methods are another class of reinforcement learning methods that seek to optimize the policy directly instead of choosing actions on the basis of their respective estimated value. Such methods could be advantageous in health care applications that entail a large number of possible actions, e.g., when recommending a wide range of drug dosages or treatment options. Clinical Applications Reinforcement learning frameworks and methods are broadly applicable to clinical settings in which decisions are made sequentially. A prominent clinical application of reinforcement learning is for treatment recommendation, which has been studied across a variety of diseases and treatments including radiation and chemotherapy for cancer, brain stimulation for epilepsy, and treatment strategies for sepsis.2–5 In such treatment recommendation settings, a policy is commonly known as a dynamic treatment regime. There are various other clinical applications of reinforcement learning including diagnosis, medical imaging, and decision support tools (see refs. 2–5 and the references therein). Reinforcement Learning in Nephrology Although there have been recent applications of machine learning in nephrology,6,7 to the best of the authors' knowledge, the application of reinforcement learning to nephrology has been primarily limited to optimizing the erythropoietin dosage in hemodialysis patients.8,9 However, there are other settings where reinforcement learning has the potential to improve patient care in nephrology. For example, reinforcement learning methods can be adopted in the treatment of the complications of AKI or CKD (Figure 1). In this problem, the state models the conditions of the patient (e.g., vital signs, laboratory test results including urine and blood tests, and urine output measurements). The action refers to the treatment options (e.g., the dosage of medications such as sodium polystyrene sulfonate, and hemodialysis). The reward models the improvement in patient conditions. Similarly, reinforcement learning can help automate and optimize the dosage of immunosuppressive drugs in kidney transplants. Challenges and Opportunities Despite the success of reinforcement learning in several simplified clinical settings, their large-scale application to patient care faces several open challenges. The complexity of human biology complicates modeling clinical decision making as a reinforcement learning problem. The state space in such settings is often enormous, which could make a purely computational approach infeasible. Moreover, modeling all potential objectives a priori as a reward function may not be feasible. To overcome these challenges and realize the potential of reinforcement learning, clinical insight can play a pivotal role. More specifically, restricting the state space to only include highly relevant clinical variables could greatly reduce the computational complexity. Furthermore, using inverse reinforcement learning,2 relevant reward functions can be learned from retrospective studies assuming the optimality of clinical decisions. Another critical challenge is addressing moral and ethical concerns. It is imperative to ensure that reinforcement learning methods do not cause harm to the patient. To this end, there exists a need for a thorough validation of such methods before their use in patient care. Hence, there is a need to go beyond retrospective studies that have been used for the proof of concept of most existing reinforcement learning methods in health care applications.2,3 The lessons learned from the success of reinforcement learning in other application areas (e.g., self-driving cars) can help navigate the path to realizing its potential in health care. Accessible open-source simulation environments that enable researchers to compare various approaches are essential to the field of reinforcement learning. OpenAI Gym is currently the leading toolkit containing a wide range of simulated environments, e.g., surgical robotics.10 The development of high-quality and reliable simulation environments for nephrology and other health care applications can facilitate the development and validation of reinforcement learning methods beyond limited retrospective studies. The adoption of methods validated in such simulation environments in actual clinical settings will require clinicians' oversight. Similar to how self-driving cars require a human driver to ensure collision avoidance, clinicians' oversight is critical to ensure the safety of the patients, especially in the early stages of the adoption of reinforcement learning methods. The data from clinicians' decisions (e.g., overruling the automated treatment recommendation) can be used to improve the reliability of autonomous systems over time and reduce the burden of clinicians' oversight.

The design and implementation of a deep reinforcement learning and quantum finance theory-inspired portfolio investment management system

Thermal processes with prolonged and variable delays pose considerable difficulties due to unpredictable system dynamics and external disturbances, often resulting in diminished control effectiveness. This work presents a hybrid control strategy that synthesizes deep reinforcement learning (DRL) strategies with nonlinear model predictive control (NMPC) to improve the robust control performance of a thermal process with a long time delay. In this approach, NMPC cost functions are formulated as learning functions to achieve control objectives in terms of thermal tracking and disturbance rejection, while an actor–critic (AC) reinforcement learning agent dynamically adjusts control actions through an adaptive policy based on the exploration and exploitation of real-time data about the thermal process. Unlike conventional NMPC approaches, the proposed framework removes the need for predefined terminal cost tuning and strict constraint formulations during the control execution at runtime, which are typically required to ensure robust stability. To assess performance, a comparative study was conducted evaluating NMPC against AC-based controllers built upon policy gradient algorithms such as the deep deterministic policy gradient (DDPG) and the twin delayed deep deterministic policy gradient (TD3). The proposed method was experimentally validated using a temperature control laboratory (TCLab) testbed featuring long and varying delays. Results demonstrate that while the NMPC–AC hybrid approach maintains tracking control performance comparable to NMPC, the proposed technique acquires adaptability while tracking and further strengthens robustness in the presence of uncertainties and disturbances under dynamic system conditions. These findings highlight the benefits of integrating DRL with NMPC to enhance reliability in thermal process control and optimize resource efficiency in thermal applications.

In today's logistics and delivery landscape, mobile robot delivery systems have attracted considerable attention due to their efficiency and adaptability. Nevertheless, current robotic delivery solutions encounter various obstacles in complex and dynamically changing environments. Traditional algorithms, for instance, struggle with processing high-dimensional and unstructured data, resulting in inefficient adaptation to real-time environmental changes, which compromises accuracy and efficiency in path planning and task execution. Moreover, the lack of robust perception and decision-making mechanisms limits the robots' ability to handle intricate scenarios and fluctuating delivery demands. To tackle these challenges, this paper proposes an optimization approach for mobile robot delivery systems that leverages deep learning. The study initially integrates a spatial attention mechanism within the model, enabling the robot to focus on critical environmental regions and dynamically adjust attention points, thus enhancing obstacle recognition and avoidance in complex settings, which improves navigation accuracy and path planning. Furthermore, the Deep Deterministic Policy Gradient (DDPG) algorithm is utilized to optimize policies, supporting efficient learning in high-dimensional continuous spaces and empowering robots to acquire effective delivery strategies in challenging environments. Finally, an end-to-end optimization approach allows the system to convert sensor inputs directly into control commands, reducing intermediate complexity and minimizing error accumulation, thereby streamlining the system’s structure. Experimental results confirm that the proposed method substantially boosts delivery system performance, excelling in key metrics like path planning accuracy, task efficiency, and system robustness. The successful integration of the spatial attention mechanism with the deep policy gradient algorithm demonstrates a valuable new approach for advancing future robot delivery system optimizations.

AQROM: A quality of service aware routing optimization mechanism based on asynchronous advantage actor-critic in software-defined networks

Hybrid deep reinforcement learning based eco-driving for low-level connected and automated vehicles along signalized corridors

In recent years, reinforcement learning (RL) has seen increasing applications in the financial industry, especially in quantitative trading and portfolio optimization when the focus is on the long-term reward rather than short-term profit. Sequential decision making and Markov decision processes are rather suited for this type of application. Through trial and error based on historical data, an agent can learn the characteristics of the market and evolve an algorithm to maximize the cumulative returns. In this work, we propose a novel RL trading algorithm utilizing random perturbation of the Q-network and account for the more realistic nonlinear transaction costs. In summary, we first design a new near-quadratic transaction cost function considering the slippage. Next, we develop a convolutional deep Q-learning network (CDQN) with multiple price input based on this cost functions. We further propose a random perturbation (rp) method to modify the learning network to solve the instability issue intrinsic to the deep Q-learning network. Finally, we use this newly developed CDQN-rp algorithm to make trading decisions based on the daily stock prices of Apple (AAPL), Meta (FB), and Bitcoin (BTC) and demonstrate its strengths over other quantitative trading methods.

Reinforcement Learning (RL) is widely adopted in robotic controlling and decision making due to its ability of adapting to the changing. However, the Deep Q-learning Network (DQN) RL systems heavily rely on CPU and GPU to accelerate the computation, which cannot meet the requirement. In this paper, we proposed a design of RL accelerator based on DQN in CPU-FPGA architecture. In this paper, we propose a design of RL accelerator based on DQN in CPU-FPGA architecture. Compared with other CPU architecture, the accelerator we proposed achieves 1.84x computing speed improvement and reduces hardware resources significantly.