With the widespread adoption of electric vehicles (EVs), navigating for EV drivers to select a cost-effective charging station has become an important yet challenging issue due to dynamic traffic conditions, fluctuating electricity prices, and potential competition from other EVs. The state-of-the-art deep reinforcement learning (DRL) algorithms for solving this task still require global information about all EVs at the execution stage, which not only increases communication costs but also raises privacy issues among EV drivers. To overcome these drawbacks, we introduce a novel generative model-enhanced multi-agent DRL algorithm that utilizes only the EV's local information while achieving performance comparable to these state-of-the-art algorithms. Specifically, the policy network is implemented on the EV side, and a Conditional Variational Autoencoder-Long Short Term Memory (CVAE-LSTM)-based recommendation model is developed to provide recommendation information. Furthermore, a novel future charging competition encoder is designed to effectively compress global information, enhancing training performance. The multi-gradient descent algorithm (MGDA) is also utilized to adaptively balance the weight between the two parts of the training objective, resulting in a more stable training process. Simulations are conducted based on a practical area in Xi\'an, China. Experimental results show that our proposed algorithm, which relies on local information, outperforms existing local information-based methods and achieves less than 8\% performance loss compared to global information-based methods.
Pok\'emon Red, a classic Game Boy JRPG, presents significant challenges as a testbed for agents, including multi-tasking, long horizons of tens of thousands of steps, hard exploration, and a vast array of potential policies. We introduce a simplistic environment and a Deep Reinforcement Learning (DRL) training methodology, demonstrating a baseline agent that completes an initial segment of the game up to completing Cerulean City. Our experiments include various ablations that reveal vulnerabilities in reward shaping, where agents exploit specific reward signals. We also discuss limitations and argue that games like Pok\'emon hold strong potential for future research on Large Language Model agents, hierarchical training algorithms, and advanced exploration methods. Source Code: https://github.com/MarcoMeter/neroRL/tree/poke_red
This study examines the secrecy performance of an uplink device-to-device (D2D) communication system enhanced by reconfigurable intelligent surfaces (RIS) while considering the presence of multiple eavesdroppers. RIS technology is employed to improve wireless communication environment by intelligently reflecting signals, thereby improving both capacity and security. We employ deep reinforcement learning (DRL) to optimize resource allocation dynamically, addressing challenges in D2D pairs and optimizing RIS positioning and phase shifts in a changing wireless environment. Our simulations demonstrate that the developed DRL-based framework significantly maximizes the sum secrecy capacity of both D2D and cellular communications, achieving higher transmission secrecy rates compared to existing benchmarks. The results highlight the effectiveness of integrating RIS with D2D communications for improved security performance.
This paper proposes a holistic framework for autonomous guidance, navigation, and task distribution among multi-drone systems operating in Global Navigation Satellite System (GNSS)-denied indoor settings. We advocate for a Deep Reinforcement Learning (DRL)-based guidance mechanism, utilising the Twin Delayed Deep Deterministic Policy Gradient algorithm. To improve the efficiency of the training process, we incorporate an Artificial Potential Field (APF)-based reward structure, enabling the agent to refine its movements, thereby promoting smoother paths and enhanced obstacle avoidance in indoor contexts. Furthermore, we tackle the issue of task distribution among cooperative UAVs through a DRL-trained Graph Convolutional Network (GCN). This GCN represents the interactions between drones and tasks, facilitating dynamic and real-time task allocation that reflects the current environmental conditions and the capabilities of the drones. Such an approach fosters effective coordination and collaboration among multiple drones during search and rescue operations or other exploratory endeavours. Lastly, to ensure precise odometry in environments lacking GNSS, we employ Light Detection And Ranging Simultaneous Localisation and Mapping complemented by a depth camera to mitigate the hallway problem. This integration offers robust localisation and mapping functionalities, thereby enhancing the systems dependability in indoor navigation. The proposed multi-drone framework not only elevates individual navigation capabilities but also optimises coordinated task allocation in complex, obstacle-laden environments. Experimental evaluations conducted in a setup tailored to meet the requirements of the NATO Sapience Autonomous Cooperative Drone Competition demonstrate the efficacy of the proposed system, yielding outstanding results and culminating in a first-place finish in the 2024 Sapience competition.
Deep Reinforcement Learning (DRL) has demonstrated potential in addressing robotic local planning problems, yet its efficacy remains constrained in highly unstructured and dynamic environments. To address these challenges, this study proposes the ColorDynamic framework. First, an end-to-end DRL formulation is established, which maps raw sensor data directly to control commands, thereby ensuring compatibility with unstructured environments. Under this formulation, a novel network, Transqer, is introduced. The Transqer enables online DRL learning from temporal transitions, substantially enhancing decision-making in dynamic scenarios. To facilitate scalable training of Transqer with diverse data, an efficient simulation platform E-Sparrow, along with a data augmentation technique leveraging symmetric invariance, are developed. Comparative evaluations against state-of-the-art methods, alongside assessments of generalizability, scalability, and real-time performance, were conducted to validate the effectiveness of ColorDynamic. Results indicate that our approach achieves a success rate exceeding 90% while exhibiting real-time capacity (1.2-1.3 ms per planning). Additionally, ablation studies were performed to corroborate the contributions of individual components. Building on this, the OkayPlan-ColorDynamic (OPCD) navigation system is presented, with simulated and real-world experiments demonstrating its superiority and applicability in complex scenarios. The codebase and experimental demonstrations have been open-sourced on our website to facilitate reproducibility and further research.
Wilderness search and rescue operations are often carried out over vast landscapes. The search efforts, however, must be undertaken in minimum time to maximize the chance of survival of the victim. Whilst the advent of cheap multicopters in recent years has changed the way search operations are handled, it has not solved the challenges of the massive areas at hand. The problem therefore is not one of complete coverage, but one of maximizing the information gathered in the limited time available. In this work we propose that a combination of a recurrent autoencoder and deep reinforcement learning is a more efficient solution to the search problem than previous pure deep reinforcement learning or optimisation approaches. The autoencoder training paradigm efficiently maximizes the information throughput of the encoder into its latent space representation which deep reinforcement learning is primed to leverage. Without the overhead of independently solving the problem that the recurrent autoencoder is designed for, it is more efficient in learning the control task. We further implement three additional architectures for a comprehensive comparison of the main proposed architecture. Similarly, we apply both soft actor-critic and proximal policy optimisation to provide an insight into the performance of both in a highly non-linear and complex application with a large observation Results show that the proposed architecture is vastly superior to the benchmarks, with soft actor-critic achieving the best performance. This model further outperformed work from the literature whilst having below a fifth of the total learnable parameters and training in a quarter of the time.
High energy consumption remains a key challenge in high-performance computing (HPC) systems, which often feature hundreds or thousands of nodes drawing substantial power even in idle or standby modes. Although powering down unused nodes can improve energy efficiency, choosing the wrong time to do so can degrade quality of service by delaying job execution. Machine learning, in particular reinforcement learning (RL), has shown promise in determining optimal times to switch nodes on or off. In this study, we enhance the performance of a deep reinforcement learning (DRL) agent for HPC power management by integrating curriculum learning (CL), a training approach that introduces tasks with gradually increasing difficulty. Using the Batsim-py simulation framework, we compare the proposed CL-based agent to both a baseline DRL method (without CL) and the conventional fixed-time timeout strategy. Experimental results confirm that an easy-to-hard curriculum outperforms other training orders in terms of reducing wasted energy usage. The best agent achieves a 3.73% energy reduction over the baseline DRL method and a 4.66% improvement compared to the best timeout configuration (shutdown every 15 minutes of idle time). In addition, it reduces average job waiting time by 9.24% and maintains a higher job-filling rate, indicating more effective resource utilization. Sensitivity tests across various switch-on durations, power levels, and cluster sizes further reveal the agent's adaptability to changing system parameters without retraining. These findings demonstrate that curriculum learning can significantly improve DRL-based power management in HPC, balancing energy savings, quality of service, and robustness to diverse configurations.
Although multi-tier vehicular Metaverse promises to transform vehicles into essential nodes -- within an interconnected digital ecosystem -- using efficient resource allocation and seamless vehicular twin (VT) migration, this can hardly be achieved by the existing techniques operating in a highly dynamic vehicular environment, since they can hardly balance multi-objective optimization problems such as latency reduction, resource utilization, and user experience (UX). To address these challenges, we introduce a novel multi-tier resource allocation and VT migration framework that integrates Graph Convolutional Networks (GCNs), a hierarchical Stackelberg game-based incentive mechanism, and Multi-Agent Deep Reinforcement Learning (MADRL). The GCN-based model captures both spatial and temporal dependencies within the vehicular network; the Stackelberg game-based incentive mechanism fosters cooperation between vehicles and infrastructure; and the MADRL algorithm jointly optimizes resource allocation and VT migration in real time. By modeling this dynamic and multi-tier vehicular Metaverse as a Markov Decision Process (MDP), we develop a MADRL-based algorithm dubbed the Multi-Objective Multi-Agent Deep Deterministic Policy Gradient (MO-MADDPG), which can effectively balances the various conflicting objectives. Extensive simulations validate the effectiveness of this algorithm that is demonstrated to enhance scalability, reliability, and efficiency while considerably improving latency, resource utilization, migration cost, and overall UX by 12.8%, 9.7%, 14.2%, and 16.1%, respectively.
This study addresses the challenge of resource scheduling optimization in edge-cloud collaborative computing using deep reinforcement learning (DRL). The proposed DRL-based approach improves task processing efficiency, reduces overall processing time, enhances resource utilization, and effectively controls task migrations. Experimental results demonstrate the superiority of DRL over traditional scheduling algorithms, particularly in managing complex task allocation, dynamic workloads, and multiple resource constraints. Despite its advantages, further improvements are needed to enhance learning efficiency, reduce training time, and address convergence issues. Future research should focus on increasing the algorithm's fault tolerance to handle more complex and uncertain scheduling scenarios, thereby advancing the intelligence and efficiency of edge-cloud computing systems.
The target defense problem involves intercepting an attacker before it reaches a designated target region using one or more defenders. This letter focuses on a particularly challenging scenario in which the attacker is more agile than the defenders, significantly increasing the difficulty of effective interception. To address this challenge, we propose a novel residual policy framework that integrates deep reinforcement learning (DRL) with the force-based Boids model. In this framework, the Boids model serves as a baseline policy, while DRL learns a residual policy to refine and optimize the defenders' actions. Simulation experiments demonstrate that the proposed method consistently outperforms traditional interception policies, whether learned via vanilla DRL or fine-tuned from force-based methods. Moreover, the learned policy exhibits strong scalability and adaptability, effectively handling scenarios with varying numbers of defenders and attackers with different agility levels.
Cross-site scripting (XSS) poses a significant threat to web application security. While Deep Learning (DL) has shown remarkable success in detecting XSS attacks, it remains vulnerable to adversarial attacks due to the discontinuous nature of its input-output mapping. These adversarial attacks employ mutation-based strategies for different components of XSS attack vectors, allowing adversarial agents to iteratively select mutations to evade detection. Our work replicates a state-of-the-art XSS adversarial attack, highlighting threats to validity in the reference work and extending it toward a more effective evaluation strategy. Moreover, we introduce an XSS Oracle to mitigate these threats. The experimental results show that our approach achieves an escape rate above 96% when the threats to validity of the replicated technique are addressed.
Digital twin (DT)-driven deep reinforcement learning (DRL) has emerged as a promising paradigm for wireless network optimization, offering safe and efficient training environment for policy exploration. However, in theory existing methods cannot always guarantee real-world performance of DT-trained policies before actual deployment, due to the absence of a universal metric for assessing DT's ability to support reliable DRL training transferrable to physical networks. In this paper, we propose the DT bisimulation metric (DT-BSM), a novel metric based on the Wasserstein distance, to quantify the discrepancy between Markov decision processes (MDPs) in both the DT and the corresponding real-world wireless network environment. We prove that for any DT-trained policy, the sub-optimality of its performance (regret) in the real-world deployment is bounded by a weighted sum of the DT-BSM and its sub-optimality within the MDP in the DT. Then, a modified DT-BSM based on the total variation distance is also introduced to avoid the prohibitive calculation complexity of Wasserstein distance for large-scale wireless network scenarios. Further, to tackle the challenge of obtaining accurate transition probabilities of the MDP in real world for the DT-BSM calculation, we propose an empirical DT-BSM method based on statistical sampling. We prove that the empirical DT-BSM always converges to the desired theoretical one, and quantitatively establish the relationship between the required sample size and the target level of approximation accuracy. Numerical experiments validate this first theoretical finding on the provable and calculable performance bounds for DT-driven DRL.
This thesis concerns the use of reinforcement learning to train neural networks to aid in the design of public transit networks. The Transit Network Design Problem (TNDP) is an optimization problem of considerable practical importance. Given a city with an existing road network and travel demands, the goal is to find a set of transit routes - each of which is a path through the graph - that collectively satisfy all demands, while minimizing a cost function that may depend both on passenger satisfaction and operating costs. The existing literature on this problem mainly considers metaheuristic optimization algorithms, such as genetic algorithms and ant-colony optimization. By contrast, we begin by taking a reinforcement learning approach, formulating the construction of a set of transit routes as a Markov Decision Process (MDP) and training a neural net policy to act as the agent in this MDP. We then show that, beyond using this policy to plan a transit network directly, it can be combined with existing metaheuristic algorithms, both to initialize the solution and to suggest promising moves at each step of a search through solution space. We find that such hybrid algorithms, which use a neural policy trained via reinforcement learning as a core component within a classical metaheuristic framework, can plan transit networks that are superior to those planned by either the neural policy or the metaheuristic algorithm. We demonstrate the utility of our approach by using it to redesign the transit network for the city of Laval, Quebec, and show that in simulation, the resulting transit network provides better service at lower cost than the existing transit network.
In this era of AI revolution, massive investments in large-scale data-driven AI systems demand high-performance computing, consuming tremendous energy and resources. This trend raises new challenges in optimizing sustainability without sacrificing scalability or performance. Among the energy-efficient alternatives of the traditional Von Neumann architecture, neuromorphic computing and its Spiking Neural Networks (SNNs) are a promising choice due to their inherent energy efficiency. However, in some real-world application scenarios such as complex continuous control tasks, SNNs often lack the performance optimizations that traditional artificial neural networks have. Researchers have addressed this by combining SNNs with Deep Reinforcement Learning (DeepRL), yet scalability remains unexplored. In this paper, we extend our previous work on SpikeRL, which is a scalable and energy efficient framework for DeepRL-based SNNs for continuous control. In our initial implementation of SpikeRL framework, we depended on the population encoding from the Population-coded Spiking Actor Network (PopSAN) method for our SNN model and implemented distributed training with Message Passing Interface (MPI) through mpi4py. Also, further optimizing our model training by using mixed-precision for parameter updates. In our new SpikeRL framework, we have implemented our own DeepRL-SNN component with population encoding, and distributed training with PyTorch Distributed package with NCCL backend while still optimizing with mixed precision training. Our new SpikeRL implementation is 4.26X faster and 2.25X more energy efficient than state-of-the-art DeepRL-SNN methods. Our proposed SpikeRL framework demonstrates a truly scalable and sustainable solution for complex continuous control tasks in real-world applications.
In this paper, we propose an event-driven Limit Order Book (LOB) model that captures twelve of the most observed LOB events in exchange-based financial markets. To model these events, we propose using the state-of-the-art Neural Hawkes process, a more robust alternative to traditional Hawkes process models. More specifically, this model captures the dynamic relationships between different event types, particularly their long- and short-term interactions, using a Long Short-Term Memory neural network. Using this framework, we construct a midprice process that captures the event-driven behavior of the LOB by simulating high-frequency dynamics like how they appear in real financial markets. The empirical results show that our model captures many of the broader characteristics of the price fluctuations, particularly in terms of their overall volatility. We apply this LOB simulation model within a Deep Reinforcement Learning Market-Making framework, where the trading agent can now complete trade order fills in a manner that closely resembles real-market trade execution. Here, we also compare the results of the simulated model with those from real data, highlighting how the overall performance and the distribution of trade order fills closely align with the same analysis on real data.
A properly designed controller can help improve the quality of experimental measurements or force a dynamical system to follow a completely new time-evolution path. Recent developments in deep reinforcement learning have made steep advances toward designing effective control schemes for fairly complex systems. However, a general simulation scheme that employs deep reinforcement learning for exerting control in stochastic systems is yet to be established. In this paper, we attempt to further bridge a gap between control theory and deep reinforcement learning by proposing a simulation algorithm that allows achieving control of the dynamics of stochastic systems through the use of trained artificial neural networks. Specifically, we use agent-based simulations where the neural network plays the role of the controller that drives local state-to-state transitions. We demonstrate the workflow and the effectiveness of the proposed control methods by considering the following two stochastic processes: particle coalescence on a lattice and a totally asymmetric exclusion process.
To guarantee global coverage and ubiquitous connectivity, the Non-terrestrial Network (NTN) technology has been regarded as a key enabling technology in the Six Generation (6G) network, which consists of the unmanned aerial vehicle (UAV), high-altitude platform (HAP), and satellite. It is noted that the unique characteristics of various NTN platforms directly impact the design and implementation of NTNs, which results in highly dynamic and heterogeneous networks. Even within the same tier, such as the space tier, the NTNs are developed based on different platforms including Low Earth Orbit (LEO), Medium Earth Orbit (MEO), and Geostationary Earth Orbit (GEO). Therefore, distributed coordination among heterogeneous NTNs remains an important challenge. Although distributed learning framework finds a wide range of applications by leveraging rich distributed data and computation resources. The explicit and systematic analysis of the individual layers' challenges, and corresponding distributed coordination solutions in heterogeneous NTNs has not been proposed yet. In this article, we first summarize the unique characteristics of each NTN platform, and analyze the corresponding impact on the design and implementation of the NTN. We then identify the communication challenges of heterogeneous NTNs in individual layers, where the potential coordinated solutions are identified. We further illustrate the multi-agent deep reinforcement learning (MADRL) algorithms tailored for coordinated solutions in heterogeneous NTNs. Last but not least, we present a case study of the user scheduling optimization problem in heterogeneous UAVs-based cellular networks, where the multi-agent deep deterministic policy gradient (MADDPG) technique is developed to validate the effectiveness of distributed coordination in heterogeneous NTNs.
The use of autonomous underwater vehicles (AUVs) for surveying, mapping, and inspecting unexplored underwater areas plays a crucial role, where maneuverability and power efficiency are key factors for extending the use of these platforms, making six degrees of freedom (6-DOF) holonomic platforms essential tools. Although Proportional-Integral-Derivative (PID) and Model Predictive Control controllers are widely used in these applications, they often require accurate system knowledge, struggle with repeatability when facing payload or configuration changes, and can be time-consuming to fine-tune. While more advanced methods based on Deep Reinforcement Learning (DRL) have been proposed, they are typically limited to operating in fewer degrees of freedom. This paper proposes a novel DRL-based approach for controlling holonomic 6-DOF AUVs using the Truncated Quantile Critics (TQC) algorithm, which does not require manual tuning and directly feeds commands to the thrusters without prior knowledge of their configuration. Furthermore, it incorporates power consumption directly into the reward function. Simulation results show that the TQC High-Performance method achieves better performance to a fine-tuned PID controller when reaching a goal point, while the TQC Energy-Aware method demonstrates slightly lower performance but consumes 30% less power on average.
Modern deep reinforcement learning (DRL) methods have made significant advances in handling continuous action spaces. However, real-world control systems--especially those requiring precise and reliable performance--often demand formal stability, and existing DRL approaches typically lack explicit mechanisms to ensure or analyze stability. To address this limitation, we propose SALSA-RL (Stability Analysis in the Latent Space of Actions), a novel RL framework that models control actions as dynamic, time-dependent variables evolving within a latent space. By employing a pre-trained encoder-decoder and a state-dependent linear system, our approach enables both stability analysis and interpretability. We demonstrated that SALSA-RL can be deployed in a non-invasive manner for assessing the local stability of actions from pretrained RL agents without compromising on performance across diverse benchmark environments. By enabling a more interpretable analysis of action generation, SALSA-RL provides a powerful tool for advancing the design, analysis, and theoretical understanding of RL systems.
Scaling up the model size and computation has brought consistent performance improvements in supervised learning. However, this lesson often fails to apply to reinforcement learning (RL) because training the model on non-stationary data easily leads to overfitting and unstable optimization. In response, we introduce SimbaV2, a novel RL architecture designed to stabilize optimization by (i) constraining the growth of weight and feature norm by hyperspherical normalization; and (ii) using a distributional value estimation with reward scaling to maintain stable gradients under varying reward magnitudes. Using the soft actor-critic as a base algorithm, SimbaV2 scales up effectively with larger models and greater compute, achieving state-of-the-art performance on 57 continuous control tasks across 4 domains. The code is available at https://dojeon-ai.github.io/SimbaV2.