PyTorchKR Papers

최신 논문

총 6,055편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2411.05228

Solving Hidden Monotone Variational Inequalities with Surrogate Losses

Deep learning has proven to be effective in a wide variety of loss minimization problems. However, many applications of interest, like minimizing projected Bellman error and min-max optimization, cannot be modelled as minimizing a scalar loss function but instead correspond to solving a variational inequality (VI) problem. This difference in setting has caused many practical challenges as naive gradient-based approaches from supervised learning tend to diverge and cycle in the VI case. In this work, we propose a principled surrogate-based approach compatible with deep learning to solve VIs. We show that our surrogate-based approach has three main benefits: (1) under assumptions that are realistic in practice (when hidden monotone structure is present, interpolation, and sufficient optimization of the surrogates), it guarantees convergence, (2) it provides a unifying perspective of existing methods, and (3) is amenable to existing deep learning optimizers like ADAM. Experimentally, we demonstrate our surrogate-based approach is effective in min-max optimization and minimizing projected Bellman error. Furthermore, in the deep reinforcement learning case, we propose a novel variant of TD(0) which is more compute and sample efficient.

arXiv:2411.05683

Data-Driven Distributed Common Operational Picture from Heterogeneous Platforms using Multi-Agent Reinforcement Learning

The integration of unmanned platforms equipped with advanced sensors promises to enhance situational awareness and mitigate the "fog of war" in military operations. However, managing the vast influx of data from these platforms poses a significant challenge for Command and Control (C2) systems. This study presents a novel multi-agent learning framework to address this challenge. Our method enables autonomous and secure communication between agents and humans, which in turn enables real-time formation of an interpretable Common Operational Picture (COP). Each agent encodes its perceptions and actions into compact vectors, which are then transmitted, received and decoded to form a COP encompassing the current state of all agents (friendly and enemy) on the battlefield. Using Deep Reinforcement Learning (DRL), we jointly train COP models and agent's action selection policies. We demonstrate resilience to degraded conditions such as denied GPS and disrupted communications. Experimental validation is performed in the Starcraft-2 simulation environment to evaluate the precision of the COPs and robustness of policies. We report less than 5% error in COPs and policies resilient to various adversarial conditions. In summary, our contributions include a method for autonomous COP formation, increased resilience through distributed prediction, and joint training of COP models and multi-agent RL policies. This research advances adaptive and resilient C2, facilitating effective control of heterogeneous unmanned platforms.

arXiv:2411.05614

Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey

Deep reinforcement learning has led to dramatic breakthroughs in the field of artificial intelligence for the past few years. As the amount of rollout experience data and the size of neural networks for deep reinforcement learning have grown continuously, handling the training process and reducing the time consumption using parallel and distributed computing is becoming an urgent and essential desire. In this paper, we perform a broad and thorough investigation on training acceleration methodologies for deep reinforcement learning based on parallel and distributed computing, providing a comprehensive survey in this field with state-of-the-art methods and pointers to core references. In particular, a taxonomy of literature is provided, along with a discussion of emerging topics and open issues. This incorporates learning system architectures, simulation parallelism, computing parallelism, distributed synchronization mechanisms, and deep evolutionary reinforcement learning. Further, we compare 16 current open-source libraries and platforms with criteria of facilitating rapid development. Finally, we extrapolate future directions that deserve further research.

arXiv:2411.05586공식 코드 · Papers with Code

Tangled Program Graphs as an alternative to DRL-based control algorithms for UAVs

Deep reinforcement learning (DRL) is currently the most popular AI-based approach to autonomous vehicle control. An agent, trained for this purpose in simulation, can interact with the real environment with a human-level performance. Despite very good results in terms of selected metrics, this approach has some significant drawbacks: high computational requirements and low explainability. Because of that, a DRL-based agent cannot be used in some control tasks, especially when safety is the key issue. Therefore we propose to use Tangled Program Graphs (TPGs) as an alternative for deep reinforcement learning in control-related tasks. In this approach, input signals are processed by simple programs that are combined in a graph structure. As a result, TPGs are less computationally demanding and their actions can be explained based on the graph structure. In this paper, we present our studies on the use of TPGs as an alternative for DRL in control-related tasks. In particular, we consider the problem of navigating an unmanned aerial vehicle (UAV) through the unknown environment based solely on the on-board LiDAR sensor. The results of our work show promising prospects for the use of TPGs in control related-tasks.

arXiv:2411.05205

Maximizing User Connectivity in AI-Enabled Multi-UAV Networks: A Distributed Strategy Generalized to Arbitrary User Distributions

Deep reinforcement learning (DRL) has been extensively applied to Multi-Unmanned Aerial Vehicle (UAV) network (MUN) to effectively enable real-time adaptation to complex, time-varying environments. Nevertheless, most of the existing works assume a stationary user distribution (UD) or a dynamic one with predicted patterns. Such considerations may make the UD-specific strategies insufficient when a MUN is deployed in unknown environments. To this end, this paper investigates distributed user connectivity maximization problem in a MUN with generalization to arbitrary UDs. Specifically, the problem is first formulated into a time-coupled combinatorial nonlinear non-convex optimization with arbitrary underlying UDs. To make the optimization tractable, a multi-agent CNN-enhanced deep Q learning (MA-CDQL) algorithm is proposed. The algorithm integrates a ResNet-based CNN to the policy network to analyze the input UD in real time and obtain optimal decisions based on the extracted high-level UD features. To improve the learning efficiency and avoid local optimums, a heatmap algorithm is developed to transform the raw UD to a continuous density map. The map will be part of the true input to the policy network. Simulations are conducted to demonstrate the efficacy of UD heatmaps and the proposed algorithm in maximizing user connectivity as compared to K-means methods.

arXiv:2411.04348

UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection

Occlusion is a longstanding difficulty that challenges the UAV-based object detection. Many works address this problem by adapting the detection model. However, few of them exploit that the UAV could fundamentally improve detection performance by changing its viewpoint. Active Object Detection (AOD) offers an effective way to achieve this purpose. Through Deep Reinforcement Learning (DRL), AOD endows the UAV with the ability of autonomous path planning to search for the observation that is more conducive to target identification. Unfortunately, there exists no available dataset for developing the UAV AOD method. To fill this gap, we released a UAV's eye view active vision dataset named UEVAVD and hope it can facilitate research on the UAV AOD problem. Additionally, we improve the existing DRL-based AOD method by incorporating the inductive bias when learning the state representation. First, due to the partial observability, we use the gated recurrent unit to extract state representations from the observation sequence instead of the single-view observation. Second, we pre-decompose the scene with the Segment Anything Model (SAM) and filter out the irrelevant information with the derived masks. With these practices, the agent could learn an active viewing policy with better generalization capability. The effectiveness of our innovations is validated by the experiments on the UEVAVD dataset. Our dataset will soon be available at https://github.com/Leo000ooo/UEVAVD_dataset.

arXiv:2411.04246공식 코드 · Papers with Code

Learning Generalizable Policy for Obstacle-Aware Autonomous Drone Racing

Autonomous drone racing has gained attention for its potential to push the boundaries of drone navigation technologies. While much of the existing research focuses on racing in obstacle-free environments, few studies have addressed the complexities of obstacle-aware racing, and approaches presented in these studies often suffer from overfitting, with learned policies generalizing poorly to new environments. This work addresses the challenge of developing a generalizable obstacle-aware drone racing policy using deep reinforcement learning. We propose applying domain randomization on racing tracks and obstacle configurations before every rollout, combined with parallel experience collection in randomized environments to achieve the goal. The proposed randomization strategy is shown to be effective through simulated experiments where drones reach speeds of up to 70 km/h, racing in unseen cluttered environments. This study serves as a stepping stone toward learning robust policies for obstacle-aware drone racing and general-purpose drone navigation in cluttered environments. Code is available at https://github.com/ErcBunny/IsaacGymEnvs.

arXiv:2411.04915

Evaluating Robustness of Reinforcement Learning Algorithms for Autonomous Shipping

Recently, there has been growing interest in autonomous shipping due to its potential to improve maritime efficiency and safety. The use of advanced technologies, such as artificial intelligence, can address the current navigational and operational challenges in autonomous shipping. In particular, inland waterway transport (IWT) presents a unique set of challenges, such as crowded waterways and variable environmental conditions. In such dynamic settings, the reliability and robustness of autonomous shipping solutions are critical factors for ensuring safe operations. This paper examines the robustness of benchmark deep reinforcement learning (RL) algorithms, implemented for IWT within an autonomous shipping simulator, and their ability to generate effective motion planning policies. We demonstrate that a model-free approach can achieve an adequate policy in the simulator, successfully navigating port environments never encountered during training. We focus particularly on Soft-Actor Critic (SAC), which we show to be inherently more robust to environmental disturbances compared to MuZero, a state-of-the-art model-based RL algorithm. In this paper, we take a significant step towards developing robust, applied RL frameworks that can be generalized to various vessel types and navigate complex port- and inland environments and scenarios.

arXiv:2411.04832

Plasticity Loss in Deep Reinforcement Learning: A Survey

Akin to neuroplasticity in human brains, the plasticity of deep neural networks enables their quick adaption to new data. This makes plasticity particularly crucial for deep Reinforcement Learning (RL) agents: Once plasticity is lost, an agent's performance will inevitably plateau because it cannot improve its policy to account for changes in the data distribution, which are a necessary consequence of its learning process. Thus, developing well-performing and sample-efficient agents hinges on their ability to remain plastic during training. Furthermore, the loss of plasticity can be connected to many other issues plaguing deep RL, such as training instabilities, scaling failures, overestimation bias, and insufficient exploration. With this survey, we aim to provide an overview of the emerging research on plasticity loss for academics and practitioners of deep reinforcement learning. First, we propose a unified definition of plasticity loss based on recent works, relate it to definitions from the literature, and discuss metrics for measuring plasticity loss. Then, we categorize and discuss numerous possible causes of plasticity loss before reviewing currently employed mitigation strategies. Our taxonomy is the first systematic overview of the current state of the field. Lastly, we discuss prevalent issues within the literature, such as a necessity for broader evaluation, and provide recommendations for future research, like gaining a better understanding of an agent's neural activity and behavior.

arXiv:2411.01338

Deep Reinforcement Learning for Trajectory and Phase Shift Optimization of Aerial RIS in CoMP-NOMA Networks

This paper explores the potential of aerial reconfigurable intelligent surfaces (ARIS) to enhance coordinated multi-point non-orthogonal multiple access (CoMP-NOMA) networks. We consider a system model where a UAV-mounted RIS assists in serving multiple users through NOMA while coordinating with multiple base stations. The optimization of UAV trajectory, RIS phase shifts, and NOMA power control constitutes a complex problem due to the hybrid nature of the parameters, involving both continuous and discrete values. To tackle this challenge, we propose a novel framework utilizing the multi-output proximal policy optimization (MO-PPO) algorithm. MO-PPO effectively handles the diverse nature of these optimization parameters, and through extensive simulations, we demonstrate its effectiveness in achieving near-optimal performance and adapting to dynamic environments. Our findings highlight the benefits of integrating ARIS in CoMP-NOMA networks for improved spectral efficiency and coverage in future wireless networks.

arXiv:2411.01451

Deep Reinforcement Learning for Optimizing Inverter Control: Fixed and Adaptive Gain Tuning Strategies for Power System Stability

This paper presents novel methods for tuning inverter controller gains using deep reinforcement learning (DRL). A Simulink-developed inverter model is converted into a dynamic link library (DLL) and integrated with a Python-based RL environment, leveraging the multi-core deployment and accelerated computing to significantly reduce RL training time. A neural network-based mechanism is developed to transform the cascaded PI controller into an actor network, allowing optimized gain tuning by an RL agent to mitigate scenarios such as subsynchronous oscillations (SSO) and initial transients. Two distinct tuning approaches are demonstrated: a fixed gain strategy, where controller gains are represented as RL policy (actor network) weights, and an adaptive gain strategy, where gains are dynamically generated as RL policy (actor network) outputs. A comparative analysis of these methods is provided, showcasing their effectiveness in stabilizing the transient performance of grid-forming and grid-following converters and deployment challenges in hardware. Experimental results are presented, demonstrating the enhanced robustness and practical applicability of the RL-tuned controller gains in real-world systems.

arXiv:2411.00995

Safe Imitation Learning-based Optimal Energy Storage Systems Dispatch in Distribution Networks

The integration of distributed energy resources (DER) has escalated the challenge of voltage magnitude regulation in distribution networks. Traditional model-based approaches, which rely on complex sequential mathematical formulations, struggle to meet real-time operational demands. Deep reinforcement learning (DRL) offers a promising alternative by enabling offline training with distribution network simulators, followed by real-time execution. However, DRL algorithms tend to converge to local optima due to limited exploration efficiency. Additionally, DRL algorithms can not enforce voltage magnitude constraints, leading to potential operational violations when implemented in the distribution network operation. This study addresses these challenges by proposing a novel safe imitation reinforcement learning (IRL) framework that combines IRL and a designed safety layer, aiming to optimize the operation of Energy Storage Systems (ESSs) in active distribution networks. The proposed safe IRL framework comprises two phases: offline training and online execution. During the offline phase, optimal state-action pairs are collected using an NLP solver, guiding the IRL policy iteration. In the online phase, the trained IRL policy's decisions are adjusted by the safety layer to maintain safety and constraint compliance. Simulation results demonstrate the efficacy of Safe IRL in balancing operational efficiency and safety, eliminating voltage violations, and maintaining low operation cost errors across various network sizes, while meeting real-time execution requirements.

arXiv:2411.00572

Enhancing Adaptive Mixed-Criticality Scheduling with Deep Reinforcement Learning

Adaptive Mixed-Criticality (AMC) is a fixed-priority preemptive scheduling algorithm for mixed-criticality hard real-time systems. It dominates many other scheduling algorithms for mixed-criticality systems, but does so at the cost of occasionally dropping jobs of less important/critical tasks, when low-priority jobs overrun their time budgets. In this paper we enhance AMC with a deep reinforcement learning (DRL) approach based on a Deep-Q Network. The DRL agent is trained off-line, and at run-time adjusts the low-criticality budgets of tasks to avoid budget overruns, while ensuring that no job misses its deadline if it does not overrun its budget. We have implemented and evaluated this approach by simulating realistic workloads from the automotive domain. The results show that the agent is able to reduce budget overruns by at least up to 50%, even when the budget of each task is chosen based on sampling the distribution of its execution time. To the best of our knowledge, this is the first use of DRL in AMC reported in the literature.

arXiv:2411.04106

A Comparative Study of Deep Reinforcement Learning for Crop Production Management

Crop production management is essential for optimizing yield and minimizing a field's environmental impact to crop fields, yet it remains challenging due to the complex and stochastic processes involved. Recently, researchers have turned to machine learning to address these complexities. Specifically, reinforcement learning (RL), a cutting-edge approach designed to learn optimal decision-making strategies through trial and error in dynamic environments, has emerged as a promising tool for developing adaptive crop management policies. RL models aim to optimize long-term rewards by continuously interacting with the environment, making them well-suited for tackling the uncertainties and variability inherent in crop management. Studies have shown that RL can generate crop management policies that compete with, and even outperform, expert-designed policies within simulation-based crop models. In the gym-DSSAT crop model environment, one of the most widely used simulators for crop management, proximal policy optimization (PPO) and deep Q-networks (DQN) have shown promising results. However, these methods have not yet been systematically evaluated under identical conditions. In this study, we evaluated PPO and DQN against static baseline policies across three different RL tasks, fertilization, irrigation, and mixed management, provided by the gym-DSSAT environment. To ensure a fair comparison, we used consistent default parameters, identical reward functions, and the same environment settings. Our results indicate that PPO outperforms DQN in fertilization and irrigation tasks, while DQN excels in the mixed management task. This comparative analysis provides critical insights into the strengths and limitations of each approach, advancing the development of more effective RL-based crop management strategies.

arXiv:2411.03820공식 코드 · Papers with Code

Beyond The Rainbow: High Performance Deep Reinforcement Learning on a Desktop PC

Rainbow Deep Q-Network (DQN) demonstrated combining multiple independent enhancements could significantly boost a reinforcement learning (RL) agent's performance. In this paper, we present "Beyond The Rainbow" (BTR), a novel algorithm that integrates six improvements from across the RL literature to Rainbow DQN, establishing a new state-of-the-art for RL using a desktop PC, with a human-normalized interquartile mean (IQM) of 7.4 on Atari-60. Beyond Atari, we demonstrate BTR's capability to handle complex 3D games, successfully training agents to play Super Mario Galaxy, Mario Kart, and Mortal Kombat with minimal algorithmic changes. Designing BTR with computational efficiency in mind, agents can be trained using a high-end desktop PC on 200 million Atari frames within 12 hours. Additionally, we conduct detailed ablation studies of each component, analyzing the performance and impact using numerous measures. Code is available at https://github.com/VIPTankz/BTR.

arXiv:2411.02853공식 코드 · Papers with Code

ADOPT: Modified Adam Can Converge with Any $β_2$ with the Optimal Rate

Adam is one of the most popular optimization algorithms in deep learning. However, it is known that Adam does not converge in theory unless choosing a hyperparameter, i.e., $\beta_2$, in a problem-dependent manner. There have been many attempts to fix the non-convergence (e.g., AMSGrad), but they require an impractical assumption that the gradient noise is uniformly bounded. In this paper, we propose a new adaptive gradient method named ADOPT, which achieves the optimal convergence rate of $\mathcal{O} ( 1 / \sqrt{T} )$ with any choice of $\beta_2$ without depending on the bounded noise assumption. ADOPT addresses the non-convergence issue of Adam by removing the current gradient from the second moment estimate and changing the order of the momentum update and the normalization by the second moment estimate. We also conduct intensive numerical experiments, and verify that our ADOPT achieves superior results compared to Adam and its variants across a wide range of tasks, including image classification, generative modeling, natural language processing, and deep reinforcement learning. The implementation is available at https://github.com/iShohei220/adopt.

arXiv:2411.02559

Dynamic Weight Adjusting Deep Q-Networks for Real-Time Environmental Adaptation

Deep Reinforcement Learning has shown excellent performance in generating efficient solutions for complex tasks. However, its efficacy is often limited by static training modes and heavy reliance on vast data from stable environments. To address these shortcomings, this study explores integrating dynamic weight adjustments into Deep Q-Networks (DQN) to enhance their adaptability. We implement these adjustments by modifying the sampling probabilities in the experience replay to make the model focus more on pivotal transitions as indicated by real-time environmental feedback and performance metrics. We design a novel Interactive Dynamic Evaluation Method (IDEM) for DQN that successfully navigates dynamic environments by prioritizing significant transitions based on environmental feedback and learning progress. Additionally, when faced with rapid changes in environmental conditions, IDEM-DQN shows improved performance compared to baseline methods. Our results indicate that under circumstances requiring rapid adaptation, IDEM-DQN can more effectively generalize and stabilize learning. Extensive experiments across various settings confirm that IDEM-DQN outperforms standard DQN models, particularly in environments characterized by frequent and unpredictable changes.

arXiv:2411.02998

Accelerating Task Generalisation with Multi-Level Skill Hierarchies

Creating reinforcement learning agents that generalise effectively to new tasks is a key challenge in AI research. This paper introduces Fracture Cluster Options (FraCOs), a multi-level hierarchical reinforcement learning method that achieves state-of-the-art performance on difficult generalisation tasks. FraCOs identifies patterns in agent behaviour and forms options based on the expected future usefulness of those patterns, enabling rapid adaptation to new tasks. In tabular settings, FraCOs demonstrates effective transfer and improves performance as it grows in hierarchical depth. We evaluate FraCOs against state-of-the-art deep reinforcement learning algorithms in several complex procedurally generated environments. Our results show that FraCOs achieves higher in-distribution and out-of-distribution performance than competitors.

arXiv:2411.02983

Autonomous Decision Making for UAV Cooperative Pursuit-Evasion Game with Reinforcement Learning

The application of intelligent decision-making in unmanned aerial vehicle (UAV) is increasing, and with the development of UAV 1v1 pursuit-evasion game, multi-UAV cooperative game has emerged as a new challenge. This paper proposes a deep reinforcement learning-based model for decision-making in multi-role UAV cooperative pursuit-evasion game, to address the challenge of enabling UAV to autonomously make decisions in complex game environments. In order to enhance the training efficiency of the reinforcement learning algorithm in UAV pursuit-evasion game environment that has high-dimensional state-action space, this paper proposes multi-environment asynchronous double deep Q-network with priority experience replay algorithm to effectively train the UAV's game policy. Furthermore, aiming to improve cooperation ability and task completion efficiency, as well as minimize the cost of UAVs in the pursuit-evasion game, this paper focuses on the allocation of roles and targets within multi-UAV environment. The cooperative game decision model with varying numbers of UAVs are obtained by assigning diverse tasks and roles to the UAVs in different scenarios. The simulation results demonstrate that the proposed method enables autonomous decision-making of the UAVs in pursuit-evasion game scenarios and exhibits significant capabilities in cooperation.

arXiv:2411.01821

IRS-Enhanced Secure Semantic Communication Networks: Cross-Layer and Context-Awared Resource Allocation

Learning-task oriented semantic communication is pivotal in optimizing transmission efficiency by extracting and conveying essential semantics tailored to specific tasks, such as image reconstruction and classification. Nevertheless, the challenge of eavesdropping poses a formidable threat to semantic privacy due to the open nature of wireless communications. In this paper, intelligent reflective surface (IRS)-enhanced secure semantic communication (IRS-SSC) is proposed to guarantee the physical layer security from a task-oriented semantic perspective. Specifically, a multi-layer codebook is exploited to discretize continuous semantic features and describe semantics with different numbers of bits, thereby meeting the need for hierarchical semantic representation and further enhancing the transmission efficiency. Novel semantic security metrics, i.e., secure semantic rate (S-SR) and secure semantic spectrum efficiency (S-SSE), are defined to map the task-oriented security requirements at the application layer into the physical layer. To achieve artificial intelligence (AI)-native secure communication, we propose a noise disturbance enhanced hybrid deep reinforcement learning (NdeHDRL)-based resource allocation scheme. This scheme dynamically maximizes the S-SSE by jointly optimizing the bits for semantic representations, reflective coefficients of the IRS, and the subchannel assignment. Moreover, we propose a novel semantic context awared state space (SCA-SS) to fusion the high-dimensional semantic space and the observable system state space, which enables the agent to perceive semantic context and solves the dimensional catastrophe problem. Simulation results demonstrate the efficiency of our proposed schemes in both enhancing the security performance and the S-SSE compared to several benchmark schemes.