UAV Confrontation and Evolutionary Upgrade Based on Multi-Agent Reinforcement Learning

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.

Traditional multi-agent reinforcement learning (MARL) algorithms typically implement global parameter sharing across various types of heterogeneous agents without meticulously differentiating between different action semantics. This approach results in the action semantic conflict problem, which decreases the generalization ability of policy networks across heterogeneous types of agents and decreases the cooperation among agents in intricate scenarios. Conversely, completely independent agent parameters significantly escalate computational costs and training complexity. To address these challenges, we introduce an adaptive MARL algorithm named Generalized Action-Prediction Optimization (GAPO). First, we introduce the Generalized Action Space (GAS), which represents the union of all agent actions with distinct semantics. All agents first compute their unified representation in the GAS, and then generate their heterogeneous action policies with different available action masks. Second, in order to further improve cooperation between heterogeneous groups, we propose a Cross-Group Prediction (CGP) loss, which adaptively predicts the action policies of other groups by leveraging trajectory information. We integrate the GAPO into both value-based and policy-based MARL algorithms, giving rise to two practical algorithms: G-QMIX and G-MAPPO. Experimental results obtained within the SMAC, MPE, MAMuJoCo, and RPE environments demonstrate the superiority of G-QMIX and G-MAPPO over several state-of-the-art MARL methods, validating the effectiveness of our proposed adaptive generalized MARL approach.

Many decision problems for complex systems that involve multiple decision makers can be formulated as a decentralized partially observable markov decision process (dec-POMDP) problem. Due to the computational difficulty with obtaining optimal policies, recent approaches to dec-POMDP often use a multi-agent reinforcement learning (MARL) algorithm. We propose a method to improve the existing cooperative MARL algorithms by adopting an imitation learning technique. For a reference policy in the imitation learning part, we use a centralized policy from a multi-agent MDP or a multi-agent POMDP model reduced from the original dec-POMDP model. In the proposed method, during the training process, we mix demonstrations from the reference policy by using a demonstration buffer. Demonstration samples from the buffer are used in the augmented policy gradient function for policy updates. We assess the performance of the proposed method for three well-known dec-POMDP benchmark problems -- Mars rover, co-operative box pushing, and dec-tiger. Experimental results indicate that augmenting the baseline MARL algorithm by mixing the demonstrations significantly improves the quality of policy solutions. With these results, we conclude that the imitation learning can enhance MARL algorithms and that policy solutions from MMDP and MPOMDP models are a reasonable reference policy to use in the proposed algorithm.

Case-based myopic reinforcement learning for satisfying target service level in supply chain

The Dual Active Bridge converter (DABC), known for its bidirectional power transfer capability and high efficiency, plays a crucial role in various applications, particularly in electric vehicles (EVs), where it facilitates energy storage, battery charging, and grid integration. The Dual Active Bridge Converter (DABC), when paired with a high-performance CLLC filter, is well-regarded for its ability to transfer power bidirectionally with high efficiency, making it valuable across a range of energy applications. While these features make the DABC highly efficient, they also complicate controller design due to nonlinear behavior, fast switching, and sensitivity to component variations. We have used a Fractional-order PID (FOPID) controller to benefit from the simple structure of classical PID controllers with lower complexity and improved flexibility because of additional filtering gains adopted in this method. However, for a FOPID controller to operate effectively under real-time conditions, its parameters must adapt continuously to changes in the system. To achieve this adaptability, a Multi-Agent Reinforcement Learning (MARL) approach is adopted, where each gain of the controller is tuned individually using the Deep Deterministic Policy Gradient (DDPG) algorithm. This structure enhances the controller’s ability to respond to external disturbances with greater robustness and adaptability. Meanwhile, finding the best initial gains in the RL structure can decrease the overall efficiency and tracking performance of the controller. To overcome this issue, Grey Wolf Optimization (GWO) algorithm is proposed to identify the most suitable initial gains for each agent, providing faster adaptation and consistent performance during the training process. The complete approach is tested using a Hardware-in-the-Loop (HIL) platform, where results confirm accurate voltage control and resilient dynamic behavior under practical conditions. In addition, the controller’s performance was validated under a battery management scenario where the DAB converter interacts with a nonlinear lithium-ion battery. The controller successfully regulated the State of Charge (SOC) through automated charging and discharging transitions, demonstrating its real-time adaptability for BMS-integrated EV systems. Consequently, the proposed MARL-FOPID controller reported better disturbance-rejection performance in different working cases compared to other conventional methods.

The research on autonomous driving based on deep reinforcement learning algorithms is a research hotspot. Traditional autonomous driving requires human involvement, and the autonomous driving algorithms based on supervised learning must be trained in advance using human experience. To deal with autonomous driving problems, this paper proposes an improved end-to-end deep deterministic policy gradient (DDPG) algorithm based on the convolutional block attention mechanism, and it is called multi-input attention prioritized deep deterministic policy gradient algorithm (MAPDDPG). Both the actor network and the critic network of the model have the same structure with symmetry. Meanwhile, the attention mechanism is introduced to help the vehicles focus on useful environmental information. The experiments are conducted in the open racing car simulator (TORCS)and the results of five experiment runs on the test tracks are averaged to obtain the final result. Compared with the state-of-the-art algorithm, the maximum reward increases from 62,207 to 116,347, and the average speed increases from 135 km/h to 193 km/h, while the number of success episodes to complete a circle increases from 96 to 147. Also, the variance of the distance from the vehicle to the center of the road is compared, and the result indicates that the variance of the DDPG is 0.6 m while that of the MAPDDPG is only 0.2 m. The above results indicate that the proposed MAPDDPG achieves excellent performance.

Reinforcement learning (RL) algorithms have been successfully applied to control tasks associated with unmanned aerial vehicles and robotics. In recent years, safe RL has been proposed to allow the safe execution of RL algorithms in industrial and mission-critical systems that operate in closed loops. However, if the system operating conditions change, such as when an unknown fault occurs, typical safe RL algorithms cannot adapt while retaining past knowledge. Continual RL algorithms have been proposed to address this issue. However, the impact of continual adaptation on the system’s safety is an understudied problem. In this paper, we study the intersection of safe and continual RL. First, we empirically demonstrate that a popular continual RL algorithm, elastic weight consolidation, does not satisfy safety constraints in nonlinear systems subject to varying operating conditions. Specifically, we study the MuJoCo HalfCheetah and Ant environments with velocity constraints and sudden joint loss non-stationarity. Then, we show that an agent trained using constrained policy optimization, a safe RL algorithm, experiences catastrophic forgetting in continual learning settings. With this in mind, we explore a simple reward-shaping method to ensure that elastic weight consolidation prioritizes remembering both safety and task performance for safety-constrained, nonlinear, and non-stationary systems.

Deep reinforcement learning is the technology of artificial neural networks in the field of decision-making and control. The traditional model-free reinforcement learning algorithm requires a large amount of environment interactive data to iterate the algorithm. This model’s performance also suffers due to low utilization of training data, while the model-based reinforcement learning (MBRL) algorithm improves the efficiency of the data, MBRL locks into low prediction accuracy. Although MBRL can utilize the additional data generated by the dynamic model, a system dynamics model with low prediction accuracy will provide low-quality data and affect the algorithm’s final result. In this paper, based on the A3C (Asynchronous Advantage Actor-Critic) algorithm, an improved model-based deep reinforcement learning algorithm using a learning degree network (MBRL-LDN) is presented. By comparing the differences between the predicted states outputted by the proposed multidynamic model and the original predicted states, the learning degree of the system dynamics model is calculated. The learning degree represents the quality of the data generated by the dynamic model and is used to decide whether to continue to interact with the dynamic model during a particular episode. Thus, low-quality data will be discarded. The superiority of the proposed method is verified by conducting extensive contrast experiments.

Reinforcement learning (RL) approaches have recently been spotlighted for use in adaptive traffic-signal control on an area-wide level. Most researchers have employed multi-agent reinforcement learning (MARL) algorithms wherein each agent shares a holistic traffic state and cooperates with other agents to reach a common goal. However, MARL algorithms cannot guarantee a global optimal solution unless the actions of all agents are fully coordinated. The present study employs a RL algorithm that recognizes an entire traffic state and jointly controls all the traffic signals of multiple intersections. With this approach, a deep Q-network (DQN) that depends solely on traffic images is extended to overcome the curse of dimensionality that is associated with a large state and action space. Several front layers in a deep convolutional neural network (CNN) to approximate the true Q-function are shared by each intersection approach. Weight parameters connecting the last hidden layer to the output layer are fixed. The proposed methodology outperforms a fixed-signal operation, a fully actuated signal operation, a multi-agent RL control without coordination, and a multi-agent RL control with partial coordination.

Design complexities of trending UAVs and the operational harsh environments necessitates Control Law formulation utilizing intelligent techniques that are both robust, model-free and adaptable. In this research, an intelligent control architecture for an Unmanned Aerial Vehicle (UAV) having an unconventional inverted V-tail design, is presented. Due to unique design of the vehicle strong roll and yaw coupling exists, making the control of vehicle challenging. To handle UAV’s inherent control complexities, while keeping them computationally acceptable, a variant of distinct Deep Reinforcement Learning (DRL) algorithm, namely Deep Deterministic Policy Gradient (DDPG) is proposed. Conventional DDPG algorithm after being modified in its learning architecture becomes capable of intelligently handling the continuous state and control space domains besides controlling the platform in its entire flight regime. This stabilization and tracking controller for the UAV achieves the goal of an optimal flight path and exhibits satisfactory performance. The paper illustrates the application of modified DDPG algorithm towards the design, while the performance of the resulting controller is assessed in simulation using dynamic model of the vehicle. Nonlinear simulations were then performed to analyze UAV performance under different environmental and launch conditions. The effectiveness of the proposed strategy is further demonstrated by comparing the results with the linear controller for the same UAV whose feedback loop gains are optimized by employing technique of optimal control theory and another DRL method named Proximal Policy Optimization (PPO). Results indicate the significance of the proposed control architecture and its inherent capability to adapt dynamically to the changing environment, thereby making it of significance utility to airborne applications.

The UAV pursuit-evasion strategy based on Deep Deterministic Policy Gradient (DDPG) algorithm is a current research hotspot. However, this algorithm has the defect of low efficiency in sample exploration. To solve this problem, this paper uses the imitation learning (IL) to improve the DDPG exploration strategy. A kind of quasiproportional guidance control law is designed to generate effective learning samples, which are used as the data of the initial experience pool of DDPG algorithm. The UAV pursuit-evasion strategy based on DDPG and imitation learning (IL-DDPG) is proposed, and the algorithm obtains the data from the experience pool for experience playback learning, which improves the exploration efficiency of the algorithm in the initial stage of training and avoids the problem of too many useless exploration in the training process. The simulation results show that the trained pursuit-UAV can flexibly adjust the flight speed and flight attitude to pursuit the evasion-UAV quickly. It also verifies that the improved DDPG algorithm is more effective than the basic DDPG algorithm to improve the training efficiency.

Multiple unmanned aerial vehicle (multi-UAV) systems have gained significant attention in applications, such as aerial surveillance and search and rescue missions. With the recent development of state-of-the-art multiagent reinforcement learning (MARL) algorithms, it is possible to train multi-UAV systems in collaborative and competitive environments. However, the inherent vulnerabilities of multiagent systems pose significant privacy and security risks when deploying general and conventional MARL algorithms. The presence of even a single Byzantine adversary within the system can severely degrade the learning performance of UAV agents. This work proposes a Byzantine-resilient MARL algorithm that leverages a combination of geometric median consensus and a robust state update model to mitigate, or even eliminate, the influence of Byzantine attacks. To validate its effectiveness and feasibility, the authors include a multi-UAV threat model, provide a guarantee of robustness, and investigate key attack parameters for multiple UAV navigation scenarios. Results from the experiments show that the average rewards during a Byzantine attack increased by up to 60% for the cooperative navigation scenario compared with conventional MARL techniques. The learning rewards generated by the baseline algorithms could not converge during training under these attacks, while the proposed method effectively converged to an optimal solution, proving its viability and correctness.

Due to the advantages of a centralized critic to estimate the Q-function value and decentralized actors to optimize the agents’ policies, counterfactual multi-agent (COMA) stands out in most multi-agent reinforcement learning (MARL) algorithms. The sharing of policy parameters can improve sampling efficiency and learning effectiveness, but it may lead to a lack of policy diversity. Hence, to balance parameter sharing and diversity among agents in COMA has been a persistent research topic. In this paper, an effective training method for a COMA policy network based on a differential evolution (DE) algorithm is proposed, named DE-COMA. DE-COMA introduces individuals in a population as computational units to construct the policy network with operations such as mutation, crossover, and selection. The average return of DE-COMA is set as the fitness function, and the best individual of policy network will be chosen for the next generation. By maintaining better parameter sharing to enhance parameter diversity, multi-agent strategies will become more exploratory. To validate the effectiveness of DE-COMA, experiments were conducted in the StarCraft II environment with 2s_vs_1sc, 2s3z, 3m, and 8m battle scenarios. Experimental results demonstrate that DE-COMA significantly outperforms the traditional COMA and most other multi-agent reinforcement learning algorithms in terms of win rate and convergence speed.

Reinforcement learning (RL) and multi-agent reinforcement learning (MARL) are disciplines concerned with defining automatically the behaviour of an agent, or a set of interacting agents, by means of reward mechanisms coming from the environment. An important research issue in the context of RL and MARL is the definition of approaches to combine the knowledge of multiple learning agents to improve the overall performance of the multi-agent system (MAS). This paper illustrates how to improve RL and MARL algorithms by utilizing results from multi-linear algebra such as tensors and tensor factorizations. In particular, the focus is on showing how to modify existing algorithms from literature to include a tensor factorization step applied to the Q-Tables learned by the individual agents to generalize the knowledge about the actions performed in the environment. The modified algorithms are then evaluated in three RL and MARL scenarios against their unmodified version to show the benefits of the tensor factorization step.

This paper presents an integrated approach to real-time processing and analysis of large-scale data streams using artificial intelligence methods, multi-agent systems, and multi-layered control architectures. Particular attention is devoted to combining technologies that are traditionally applied separately: unmanned aerial vehicle (UAV) control systems, situational centers, streaming video services, and distributed sensor networks. The proposed model accounts for the stochastic nature of the environment, the dynamic behaviour of data flows, and resource constraints, which are critical factors for real-time systems. The study develops a multi-level multi-agent architecture that includes central, regional, and edge nodes, as well as local agents such as drones, sensors, and client-side video devices. A mathematical formalization of agent interaction and reward functions is proposed to ensure a balance between service quality, latency, packet loss, and energy consumption. The use of multi-agent reinforcement learning (MARL) algorithms is introduced to support adaptive decision-making in real time, along with the development of a digital twin of the environment for predicting future system states using deep and generative models. The results demonstrate that the integration of edge computing, hierarchical decision-making, and local agent autonomy significantly enhances system resilience, provides stable performance under external disturbances, and enables effective infrastructure scaling. The findings form a scientific foundation for designing adaptive, robust, and self-learning next-generation digital ecosystems capable of intelligent processing of large data streams in real time