Drone Altitude Control with Reinforcement Learning

Aiming at the frequency instability and the increase of control cost caused by the uncertainty of the island microgrid, this paper proposes a multi-objective control strategy for the island microgrid based on the Soft Actor Critic (SAC) algorithm. Firstly, considering the influence of the output distribution of micro gas turbines on the control cost, a multi-objective control model that coordinates control cost and frequency stability is constructed. Secondly, in order to cope with the sparse reward task of multi-objective control, this paper takes the frequency deviation and control cost as the state set, takes the unit output as the action set, and designs the corresponding reward function, thus completing the process design of the multi-objective control strategy. Finally, the calculation example shows that the SAC controller can effectively reduce the control cost on the premise of ensuring the frequency regulation requirements of the microgrid, and the comprehensive control effect is far superior to traditional control methods such as PI control and fuzzy control.

Great attention has been attracted to the growing energy consumption of the subway system. It is significant to investigate the energy-efficient train control methodology which is regarded as an effective way to cut down the energy cost of the subway system. In this paper, a soft actor-critic-based method is proposed to determine the optimal driving strategy. Firstly, the inverse problem of the energy-efficient train control problem, i.e., minimizing the trip time with constant traction energy, is presented, and it is converted to a finite Markov decision process which can be solved with deep reinforcement learning (DRL) algorithms. Secondly, the soft actor-critic (SAC) algorithm is proposed to determine the optimal driving strategy. Finally, the effectiveness of the proposed method is verified via the case studies. It is also illustrated that the SAC-based method has a good performance in robustness and stability. Moreover, compared with other DRL algorithms such as the deep Q network (DQN), the SAC-based method saves about 66% training steps on average to achieve the optimum, which reduces the computational resources.

With the continuous progress of UAV technology and the rapid development of mobile edge computing (MEC), the UAV-assisted MEC system has shown great application potential in special fields such as disaster rescue and emergency response. However, traditional deep reinforcement learning (DRL) decision-making methods suffer from limitations such as difficulty in balancing multiple objectives and training convergence when making mixed action space decisions for UAV path planning and task offloading. This article innovatively proposes a hybrid decision framework based on the improved Dynamic Adaptive Genetic Optimization Algorithm (DAGOA) and soft actor–critic with hierarchical action decomposition, an uncertainty-quantified critic ensemble, and adaptive entropy temperature, where DAGOA performs an effective search and optimization in discrete action space, while SAC can perform fine control and adjustment in continuous action space. By combining the above algorithms, the joint optimization of drone path planning and task offloading can be achieved, improving the overall performance of the system. The experimental results show that the framework offers significant advantages in improving system performance, reducing energy consumption, and enhancing task completion efficiency. When the system adopts a hybrid decision framework, the reward score increases by a maximum of 153.53% compared to pure deep reinforcement learning algorithms for decision-making. Moreover, it can achieve an average improvement of 61.09% on the basis of various reinforcement learning algorithms such as proposed SAC, proximal policy optimization (PPO), deep deterministic policy gradient (DDPG), and twin delayed deep deterministic policy gradient (TD3).

Due to the excessive degree of freedom of the space flexible manipulator, we can hardly obtain its accurate dynamic model for its motion planning. In this work, we formulate the precise motion control of the free-floating space piecewise constant curvature (FSPCC) continuum manipulator (i.e. space flexible manipulator) as a sparse reward problem in reinforcement learning, and use the Soft Actor-Critic (SAC) algorithm along with the Random Network Distillation (RND) method to train the optimal policies. Firstly, we use the RND method to jointly train a predictive network and a fixed network. The discrepancy between the output values of the two networks is served as an internal reward for the environment. Secondly, the SAC algorithm aims to maximize the expected return and the entropy of the policy. Policies with high entropy will successfully complete the task while acting as randomly as possible. Finally, the internal rewards tend to incentivize the agent to explore more widely for faster convergence of the algorithm. We applied this method to the FSPCC continuum manipulator simulation model and the results demonstrate that the SAC algorithm together with RND method can control the FSPCC continuum manipulator to catch the target quickly, even in the presence of sparse reward.

The present study applies a Deep Reinforcement Learning (DRL) algorithm to Active Flow Control (AFC) of a two-dimensional flow around a confined square cylinder. Specifically, the Soft Actor-Critic (SAC) algorithm is employed to modulate the flow of a pair of synthetic jets placed on the upper and lower surfaces of the confined squared cylinder in flow configurations characterized by Re of 100, 200, 300, and 400. The investigation starts with an analysis of the baseline flow in the absence of active control. It is observed that at Re = 100 and Re = 200, the vortex shedding exhibits mono-frequency characteristics. Conversely, at Re = 300 and Re = 400, the vortex shedding is dominated by multiple frequencies, which is indicative of more complex flow features. With the application of the SAC algorithm, we demonstrate the capability of DRL-based control in effectively suppressing vortex shedding, while significantly diminishing drag and fluctuations in lift. Quantitatively, the data-driven active control strategy results in a drag reduction of approximately 14.4%, 26.4%, 38.9%, and 47.0% for Re = 100, 200, 300, and 400, respectively. To understand the underlying control mechanism, we also present detailed flow field comparisons, which showcase the adaptability of DRL in devising distinct control strategies tailored to the dynamic conditions at varying Re. These findings substantiate the ability of DRL to control chaotic, multi-frequency dominated vortex shedding phenomena, underscoring the robustness of DRL in complex AFC problems.

With the development of artificial intelligence, intelligent communication jamming decision making is an important research direction of cognitive electronic warfare. In this paper, we consider a complex intelligent jamming decision scenario in which both communication parties choose to adjust physical layer parameters to avoid jamming in a non-cooperative scenario and the jammer achieves accurate jamming by interacting with the environment. However, when the situation becomes complex and large in number, traditional reinforcement learning suffers from the problems of failure to converge and a high number of interactions, which are fatal and unrealistic in a real warfare environment. To solve this problem, we propose a deep reinforcement learning based and maximum-entropy-based soft actor-critic (SAC) algorithm. In the proposed algorithm, we add an improved Wolpertinger architecture to the original SAC algorithm in order to reduce the number of interactions and improve the accuracy of the algorithm. The results show that the proposed algorithm shows excellent performance in various scenarios of jamming and achieves accurate, fast, and continuous jamming for both sides of the communication.

Energy management strategy for electro-hydraulic hybrid electric vehicles considering optimal mode switching: A soft actor-critic approach trained on a multi-modal driving cycle

Approximation biases of value functions are considered a key problem in reinforcement learning (RL). In particular, existing RL algorithms are hindered by overestimation and underestimation biases, i.e., value mismatching between RL's actual returns and action-value approximations limits the performance of RL algorithms. In this article, we first develop a new synthesis loss function for RL's action-value estimation integrating a regularization term and a modified "clipped double Q-learning" structure for solving overestimation and underestimation biases. To minimize the differences between action-value estimations and actual returns in RL, we develop a new discrepancy function to determine the type and magnitude of approximation biases. Then, two coefficients embedded in the synthesis loss are automatically tuned by minimizing the discrepancy function during training to minimize approximation biases. We further design a new actor-critic (AC) algorithm, named AC with synthesis loss (ACSL), by integrating the synthesis loss function and an error-controlled mechanism. Experimental results on continuous control tasks illustrate that the proposed ACSL algorithm outperforms other cutting-edge RL methods in many tasks and that the proposed synthesis loss function is easily implemented into other algorithms and significantly reduces approximation biases while improving performance. The proposed method can successfully handle many complex continuous control tasks and can greatly outperform other state-of-the-art algorithms on most tasks.

Dynamic radio resource management is essential for optimising performance in an open radio access network (RAN). However, traditional methods often struggle with realtime decision-making and resource allocation in dynamic environments. Intelligent solutions, such as xApps running on near-real-time (near-RT) RAN Intelligent Controllers (RICs), offer promising advancements in adaptability and efficiency. This paper evaluates the performance of 5 reinforcement learning (RL) algorithms: Advantage Actor-Critic (A2C), Asynchronous Advantage Actor-Critic (A3C), Proximal Policy Optimisation (PPO), Deep Q-Network (DQN) and Soft Actor Critic (SAC), which were implemented as xApps for dynamic resource allocation in an open RAN setting. We analyse how effectively each algorithm learns to allocate resources by associating user equipment (UE), connected to different service classes: video, voice and data, to base stations as they move through a simulated network environment. Additionally, we evaluate the agents by comparing their throughput, latency and reward performance, and validate the results by examining them over 5 seeds run under the same network configurations. Our findings reveal that DQN achieves the highest rewards and fastest convergence, followed by SAC, PPO offers stable learning at moderate reward levels, while A2C and A3C show slower convergence and lower rewards. These results demonstrate both the advantages and limitations of using RL for dynamic resource management in open RAN systems. Finally, we discuss future directions, such as exploring multiagent systems and deploying xApps in real-world open RAN testbeds, to advance practical applications.

By addressing the drawbacks of static optimization techniques, this research seeks to improve the dynamic energy management of thermoelectric generators (TEGs). Finding the best deep reinforcement learning (DRL) algorithm to maximize energy distribution, prolong battery life, and boost system efficiency in the face of the variable conditions present in waste heat recovery systems is the goal. The TEG system was modeled using the Markov decision process and implemented in a computer-simulated environment. Three advanced DRL algorithms were used: soft actor-critic (SAC), proximal policy optimization (PPO), and deep Q-networks (DQN); which were trained to act as intelligent controllers. The performance of each algorithm was systematically evaluated and compared using key metrics, including average cumulative reward, battery health, system efficiency, and a novel metric termed the energy fulfillment rate, which measures the ability to meet demand while storing surplus energy. The comparative analysis revealed a critical trade-off between maximizing performance and ensuring hardware longevity. The SAC algorithm demonstrated the best overall performance, achieving the highest average reward (− 7.03) and energy fulfillment rate (22.84%). However, the A2C, DDPG, and PPO algorithms all achieved a perfect average battery health of 100.00%, highlighting their superior capability for preserving system longevity, albeit with slightly lower rewards. The DQN algorithm consistently showed the least effective performance across all metrics, particularly in maintaining battery health (60.73%). The SAC algorithm is the most suitable of the methods tested for dynamically managing TEG systems. Its underlying principle of maximization of entropy enables a better exploration of control strategies, leading to a better balance between immediate energy dispatch and long-term storage goals. The findings confirm the significant potential of DRL to create efficient and adaptive controllers for renewable energy applications, although further validation of physical hardware is required to confirm real-world viability.Supplementary InformationThe online version contains supplementary material available at 10.1038/s41598-025-27210-7.

Aim and ApproachLarge cooling water system has great potential of energy saving due to improper operation control. The coupled hydraulic and thermodynamic characteristics among chillers, pumps, and cooling towers lead to the difficulty of cooling water system operation. This study investigates an advanced control approach of multi-agent reinforcement learning (RL) for a large cooling water system. The multiple RL agents interact with each other to deal with the complex coupled characteristics in the cooling water system. The proposed approach is implemented in a real-world cooling water system and validated with experiments.Scientific Innovation and RelevanceIn this study, a multi-agent RL approach is proposed to separately control the chillers, pumps, and cooling towers in the cooling water system. The soft actor critic algorithm is used in the RL agent, as it is an efficient and advanced RL algorithm for continuous and discrete control problems. The agents are designed to have private states, private actions, and shared rewards. The reward functions are carefully designed to balance the agents for global optima.To provide a realistic environment for RL training, a detailed physical modeling platform of a cooling water system is established and validated. This platform is capable of hydraulic and thermodynamic calculation of cooling water systems with customized numbers and characteristics of chillers, pumps, and cooling towers, which is scalable for different cooling water systems.The proposed multi-agent RL controller is implemented in the building automation system of a real cooling water system. A one-month experimental study of the multi-agent RL performance is conducted. The proposed multi-agent RL controller is compared with a single-agent RL controller and a rule-based controller through real-world experiments to demonstrate the energy performance. This is a pilot study of multi-agent RL approach to real-world cooling water system control.Preliminary Results and ConclusionsThe preliminary simulation study is conducted in the established cooling water system model. The electricity consumption simulation error is 4.0% in coefficient of variation of mean absolute error (CVMAE) compared with the measured 15-minute electricity consumption. The 6-month simulation shows that the single-agent RL can save 6.2% energy from the rule-based control, while the multi-agent RL can save 7.2% electricity consumption of the cooling water system. In the following study, the multi-agent RL implementation will be practiced with more experiments and applications for cooling water system control.

This paper investigates the error accumulation problem in centralized training and decentralized execution (CTDE) policy‐based multi‐agent reinforcement learning (MARL) algorithms, which arises from local observation inaccuracies. To address this issue, we propose a novel MARL algorithm that incorporates imitation learning using local observations. Firstly, by analysing the multi‐agent proximal policy optimization algorithm and examining the problems arising when global states are replaced with local observations, it is proved that insufficient observations can lead to information loss, thereby introducing errors of advantage function, and it is demonstrated that the generalized advantage estimation method accumulates errors during the training process. Then, imitation learning is introduced and a novel training framework that combines reinforcement learning and imitation learning is proposed. During the reinforcement learning phase, an MARL agent trained with global observations acts as an expert. Subsequently, imitation learning is applied to train another agent that mimics the expert's decisions using only local observations. Finally, the effectiveness of this algorithm is verified in some commonly used multi‐agent environments, which demonstrates its superior performance compared to traditional multi‐agent reinforcement learning algorithms.

Owing to the unique advantages of low cost and controllability, reconfigurable intelligent surface (RIS) is a promising candidate to address the blockage issue in millimeter wave (mmWave) communication systems, consequently has captured widespread attention in recent years. However, the joint active beamforming and passive beamforming design is an arduous task due to the high computational complexity and the dynamic changes of wireless environment. In this paper, we consider a RIS-assisted multi-user multiple-input single-output (MU-MISO) mmWave system and aim to develop a deep reinforcement learning (DRL) based algorithm to jointly design active hybrid beamformer at the base station (BS) side and passive beamformer at the RIS side. By employing an advanced soft actor-critic (SAC) algorithm, we propose a maximum entropy based DRL algorithm, which can explore more stochastic policies than deterministic policy, to design active analog precoder and passive beamformer simultaneously. Then, the digital precoder is determined by minimum mean square error (MMSE) method. The experimental results demonstrate that our proposed SAC algorithm can achieve better performance compared with conventional optimization algorithm and DRL algorithm.

The intermittence and fluctuation of renewable energy aggravate the power fluctuation of the power grid and pose a severe challenge to the frequency stability of the power system. Thermostatically controlled loads can participate in the frequency regulation of the power grid due to their flexibility. Aiming to solve the problem of the traditional control methods, which have limited adjustment ability, and to have a positive influence on customers, a deep reinforcement learning control strategy based on the framework of soft actor–critic is proposed, considering customer satisfaction. Firstly, the energy storage index and the discomfort index of different users are defined. Secondly, the fuzzy comprehensive evaluation method is applied to evaluate customer satisfaction. Then, the multi-agent models of thermostatically controlled loads are established based on the soft actor–critic algorithm. The models are trained by using the local information of thermostatically controlled loads, and the comprehensive evaluation index fed back by users and the frequency deviation. After training, each agent can realize the cooperative response of thermostatically controlled loads to the system frequency only by relying on the local information. The simulation results show that the proposed strategy can not only reduce the frequency fluctuation, but also improve customer satisfaction.

This paper presents an integrated Reinforcement Learning (RL) and Model Predictive Control (MPC) framework for autonomous satellite docking with a partially filled fuel tank. Traditional docking control faces challenges due to fuel sloshing in microgravity, which induces unpredictable forces affecting stability. To address this, we integrate Proximal Policy Optimization (PPO) and Soft Actor-Critic (SAC) RL algorithms with MPC, leveraging MPC’s predictive capabilities to accelerate RL training and improve control robustness. The proposed approach is validated through Zero-G Lab of SnT experiments for planar stabilization and high-fidelity numerical simulations for 6-DOF docking with fuel sloshing dynamics. Simulation results demonstrate that SAC-MPC achieves superior docking accuracy, higher success rates, and lower control effort, outperforming standalone RL and PPO-MPC methods. This study advances fuel-efficient and disturbance-resilient satellite docking, enhancing the feasibility of on-orbit refueling and servicing missions.