PyTorchKR Papers

최신 논문

총 6,055편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2407.17822공식 코드 · Papers with Code

Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and quality

Flow control is key to maximize energy efficiency in a wide range of applications. However, traditional flow-control methods face significant challenges in addressing non-linear systems and high-dimensional data, limiting their application in realistic energy systems. This study advances deep-reinforcement-learning (DRL) methods for flow control, particularly focusing on integrating group-invariant networks and positional encoding into DRL architectures. Our methods leverage multi-agent reinforcement learning (MARL) to exploit policy invariance in space, in combination with group-invariant networks to ensure local symmetry invariance. Additionally, a positional encoding inspired by the transformer architecture is incorporated to provide location information to the agents, mitigating action constraints from strict invariance. The proposed methods are verified using a case study of Rayleigh-B\'enard convection, where the goal is to minimize the Nusselt number Nu. The group-invariant neural networks (GI-NNs) show faster convergence compared to the base MARL, achieving better average policy performance. The GI-NNs not only cut DRL training time in half but also notably enhance learning reproducibility. Positional encoding further enhances these results, effectively reducing the minimum Nu and stabilizing convergence. Interestingly, group invariant networks specialize in improving learning speed and positional encoding specializes in improving learning quality. These results demonstrate that choosing a suitable feature-representation method according to the purpose as well as the characteristics of each control problem is essential. We believe that the results of this study will not only inspire novel DRL methods with invariant and unique representations, but also provide useful insights for industrial applications.

arXiv:2407.18066

Multi-Agent Deep Reinforcement Learning for Resilience Optimization in 5G RAN

Resilience is defined as the ability of a network to resist, adapt, and quickly recover from disruptions, and to continue to maintain an acceptable level of services from users' perspective. With the advent of future radio networks, including advanced 5G and upcoming 6G, critical services become integral to future networks, requiring uninterrupted service delivery for end users. Unfortunately, with the growing network complexity, user mobility and diversity, it becomes challenging to scale current resilience management techniques that rely on local optimizations to large dense network deployments. This paper aims to address this problem by globally optimizing the resilience of a dense multi-cell network based on multi-agent deep reinforcement learning. Specifically, our proposed solution can dynamically tilt cell antennas and reconfigure transmit power to mitigate outages and increase both coverage and service availability. A multi-objective optimization problem is formulated to simultaneously satisfy resiliency constraints while maximizing the service quality in the network area in order to minimize the impact of outages on neighbouring cells. Extensive simulations then demonstrate that with our proposed solution, the average service availability in terms of user throughput can be increased by up to 50-60% on average, while reaching a coverage availability of 99% in best cases.

arXiv:2407.17980

Personalized and Context-aware Route Planning for Edge-assisted Vehicles

Conventional route planning services typically offer the same routes to all drivers, focusing primarily on a few standardized factors such as travel distance or time, overlooking individual driver preferences. With the inception of autonomous vehicles expected in the coming years, where vehicles will rely on routes decided by such planners, there arises a need to incorporate the specific preferences of each driver, ensuring personalized navigation experiences. In this work, we propose a novel approach based on graph neural networks (GNNs) and deep reinforcement learning (DRL), aimed at customizing routes to suit individual preferences. By analyzing the historical trajectories of individual drivers, we classify their driving behavior and associate it with relevant road attributes as indicators of driver preferences. The GNN is capable of representing the road network as graph-structured data effectively, while DRL is capable of making decisions utilizing reward mechanisms to optimize route selection with factors such as travel costs, congestion level, and driver satisfaction. We evaluate our proposed GNN-based DRL framework using a real-world road network and demonstrate its ability to accommodate driver preferences, offering a range of route options tailored to individual drivers. The results indicate that our framework can select routes that accommodate driver's preferences with up to a 17% improvement compared to a generic route planner, and reduce the travel time by 33% (afternoon) and 46% (evening) relatively to the shortest distance-based approach.

arXiv:2407.17303

MoveLight: Enhancing Traffic Signal Control through Movement-Centric Deep Reinforcement Learning

This paper introduces MoveLight, a novel traffic signal control system that enhances urban traffic management through movement-centric deep reinforcement learning. By leveraging detailed real-time data and advanced machine learning techniques, MoveLight overcomes the limitations of traditional traffic signal control methods. It employs a lane-level control approach using the FRAP algorithm to achieve dynamic and adaptive traffic signal control, optimizing traffic flow, reducing congestion, and improving overall efficiency. Our research demonstrates the scalability and effectiveness of MoveLight across single intersections, arterial roads, and network levels. Experimental results using real-world datasets from Cologne and Hangzhou show significant improvements in metrics such as queue length, delay, and throughput compared to existing methods. This study highlights the transformative potential of deep reinforcement learning in intelligent traffic signal control, setting a new standard for sustainable and efficient urban transportation systems.

arXiv:2407.16877

Neural Network-Based Bandit: A Medium Access Control for the IIoT Alarm Scenario

Efficient Random Access (RA) is critical for enabling reliable communication in Industrial Internet of Things (IIoT) networks. Herein, we propose a deep reinforcement learning based distributed RA scheme, entitled Neural Network-Based Bandit (NNBB), for the IIoT alarm scenario. In such a scenario, the devices may detect a common critical event, and the goal is to ensure the alarm information is delivered successfully from at least one device. The proposed NNBB scheme is implemented at each device, where it trains itself online and establishes implicit inter-device coordination to achieve the common goal. Devices can transmit simultaneously on multiple orthogonal channels and each possible transmission pattern constitutes a possible action for the NNBB, which uses a deep neural network to determine the action. Our simulation results show that as the number of devices in the network increases, so does the performance gain of the NNBB compared to the Multi-Armed Bandit (MAB) RA benchmark. For instance, NNBB experiences a 7% success rate drop when there are four channels and the number of devices increases from 10 to 60, while MAB faces a 25% drop.

arXiv:2407.15476

MODRL-TA:A Multi-Objective Deep Reinforcement Learning Framework for Traffic Allocation in E-Commerce Search

Traffic allocation is a process of redistributing natural traffic to products by adjusting their positions in the post-search phase, aimed at effectively fostering merchant growth, precisely meeting customer demands, and ensuring the maximization of interests across various parties within e-commerce platforms. Existing methods based on learning to rank neglect the long-term value of traffic allocation, whereas approaches of reinforcement learning suffer from balancing multiple objectives and the difficulties of cold starts within realworld data environments. To address the aforementioned issues, this paper propose a multi-objective deep reinforcement learning framework consisting of multi-objective Q-learning (MOQ), a decision fusion algorithm (DFM) based on the cross-entropy method(CEM), and a progressive data augmentation system(PDA). Specifically. MOQ constructs ensemble RL models, each dedicated to an objective, such as click-through rate, conversion rate, etc. These models individually determine the position of items as actions, aiming to estimate the long-term value of multiple objectives from an individual perspective. Then we employ DFM to dynamically adjust weights among objectives to maximize long-term value, addressing temporal dynamics in objective preferences in e-commerce scenarios. Initially, PDA trained MOQ with simulated data from offline logs. As experiments progressed, it strategically integrated real user interaction data, ultimately replacing the simulated dataset to alleviate distributional shifts and the cold start problem. Experimental results on real-world online e-commerce systems demonstrate the significant improvements of MODRL-TA, and we have successfully deployed MODRL-TA on an e-commerce search platform.

arXiv:2407.14714공식 코드 · Papers with Code

Unveiling the Decision-Making Process in Reinforcement Learning with Genetic Programming

Despite tremendous progress, machine learning and deep learning still suffer from incomprehensible predictions. Incomprehensibility, however, is not an option for the use of (deep) reinforcement learning in the real world, as unpredictable actions can seriously harm the involved individuals. In this work, we propose a genetic programming framework to generate explanations for the decision-making process of already trained agents by imitating them with programs. Programs are interpretable and can be executed to generate explanations of why the agent chooses a particular action. Furthermore, we conduct an ablation study that investigates how extending the domain-specific language by using library learning alters the performance of the method. We compare our results with the previous state of the art for this problem and show that we are comparable in performance but require much less hardware resources and computation time.

arXiv:2407.15403

Offline Imitation Learning Through Graph Search and Retrieval

Imitation learning is a powerful machine learning algorithm for a robot to acquire manipulation skills. Nevertheless, many real-world manipulation tasks involve precise and dexterous robot-object interactions, which make it difficult for humans to collect high-quality expert demonstrations. As a result, a robot has to learn skills from suboptimal demonstrations and unstructured interactions, which remains a key challenge. Existing works typically use offline deep reinforcement learning (RL) to solve this challenge, but in practice these algorithms are unstable and fragile due to the deadly triad issue. To overcome this problem, we propose GSR, a simple yet effective algorithm that learns from suboptimal demonstrations through Graph Search and Retrieval. We first use pretrained representation to organize the interaction experience into a graph and perform a graph search to calculate the values of different behaviors. Then, we apply a retrieval-based procedure to identify the best behavior (actions) on each state and use behavior cloning to learn that behavior. We evaluate our method in both simulation and real-world robotic manipulation tasks with complex visual inputs, covering various precise and dexterous manipulation skills with objects of different physical properties. GSR can achieve a 10% to 30% higher success rate and over 30% higher proficiency compared to baselines. Our project page is at https://zhaohengyin.github.io/gsr.

arXiv:2407.13790

SOC-Boundary and Battery Aging Aware Hierarchical Coordination of Multiple EV Aggregates Among Multi-stakeholders with Multi-Agent Constrained Deep Reinforcement Learning

As electric vehicles (EV) become more prevalent and advances in electric vehicle electronics continue, vehicle-to-grid (V2G) techniques and large-scale scheduling strategies are increasingly important to promote renewable energy utilization and enhance the stability of the power grid. This study proposes a hierarchical multistakeholder V2G coordination strategy based on safe multi-agent constrained deep reinforcement learning (MCDRL) and the Proof-of-Stake algorithm to optimize benefits for all stakeholders, including the distribution system operator (DSO), electric vehicle aggregators (EVAs) and EV users. For DSO, the strategy addresses load fluctuations and the integration of renewable energy. For EVAs, energy constraints and charging costs are considered. The three critical parameters of battery conditioning, state of charge (SOC), state of power (SOP), and state of health (SOH), are crucial to the participation of EVs in V2G. Hierarchical multi-stakeholder V2G coordination significantly enhances the integration of renewable energy, mitigates load fluctuations, meets the energy demands of the EVAs, and reduces charging costs and battery degradation simultaneously.

arXiv:2407.15784

Diffusion Model Based Resource Allocation Strategy in Ultra-Reliable Wireless Networked Control Systems

Diffusion models are vastly used in generative AI, leveraging their capability to capture complex data distributions. However, their potential remains largely unexplored in the field of resource allocation in wireless networks. This paper introduces a novel diffusion model-based resource allocation strategy for Wireless Networked Control Systems (WNCSs) with the objective of minimizing total power consumption through the optimization of the sampling period in the control system, and blocklength and packet error probability in the finite blocklength regime of the communication system. The problem is first reduced to the optimization of blocklength only based on the derivation of the optimality conditions. Then, the optimization theory solution collects a dataset of channel gains and corresponding optimal blocklengths. Finally, the Denoising Diffusion Probabilistic Model (DDPM) uses this collected dataset to train the resource allocation algorithm that generates optimal blocklength values conditioned on the channel state information (CSI). Via extensive simulations, the proposed approach is shown to outperform previously proposed Deep Reinforcement Learning (DRL) based approaches with close to optimal performance regarding total power consumption. Moreover, an improvement of up to eighteen-fold in the reduction of critical constraint violations is observed, further underscoring the accuracy of the solution.

arXiv:2407.15168

Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers are designed to induce a deviation in the behaviour of a backdoored agent while blending into the expected data distribution to evade detection. Through experiments conducted in the Atari Breakout environment, we demonstrate the limitations of current sanitisation methods when faced with such triggers and investigate why they present a challenging defence problem. We then evaluate the hypothesis that backdoor triggers might be easier to detect in the neural activation space of the DRL agent's policy network. Our statistical analysis shows that indeed the activation patterns in the agent's policy network are distinct in the presence of a trigger, regardless of how well the trigger is concealed in the environment. Based on this, we propose a new defence approach that uses a classifier trained on clean environment samples and detects abnormal activations. Our results show that even lightweight classifiers can effectively prevent malicious actions with considerable accuracy, indicating the potential of this research direction even against sophisticated adversaries.

arXiv:2407.14486공식 코드 · Papers with Code

Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent

Financial portfolio management investment policies computed quantitatively by modern portfolio theory techniques like the Markowitz model rely on a set on assumptions that are not supported by data in high volatility markets. Hence, quantitative researchers are looking for alternative models to tackle this problem. Concretely, portfolio management is a problem that has been successfully addressed recently by Deep Reinforcement Learning (DRL) approaches. In particular, DRL algorithms train an agent by estimating the distribution of the expected reward of every action performed by an agent given any financial state in a simulator. However, these methods rely on Deep Neural Networks model to represent such a distribution, that although they are universal approximator models, they cannot explain its behaviour, given by a set of parameters that are not interpretable. Critically, financial investors policies require predictions to be interpretable, so DRL agents are not suited to follow a particular policy or explain their actions. In this work, we developed a novel Explainable Deep Reinforcement Learning (XDRL) approach for portfolio management, integrating the Proximal Policy Optimization (PPO) with the model agnostic explainable techniques of feature importance, SHAP and LIME to enhance transparency in prediction time. By executing our methodology, we can interpret in prediction time the actions of the agent to assess whether they follow the requisites of an investment policy or to assess the risk of following the agent suggestions. To the best of our knowledge, our proposed approach is the first explainable post hoc portfolio management financial policy of a DRL agent. We empirically illustrate our methodology by successfully identifying key features influencing investment decisions, which demonstrate the ability to explain the agent actions in prediction time.

arXiv:2407.14151공식 코드 · Papers with Code

A Comparative Study of Deep Reinforcement Learning Models: DQN vs PPO vs A2C

This study conducts a comparative analysis of three advanced Deep Reinforcement Learning models: Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), and Advantage Actor-Critic (A2C), within the BreakOut Atari game environment. Our research assesses the performance and effectiveness of these models in a controlled setting. Through rigorous experimentation, we examine each model's learning efficiency, strategy development, and adaptability under dynamic game conditions. The findings provide critical insights into the practical applications of these models in game-based learning environments and contribute to the broader understanding of their capabilities. The code is publicly available at github.com/Neilus03/DRL_comparative_study.

arXiv:2407.13947

Event-Triggered Reinforcement Learning Based Joint Resource Allocation for Ultra-Reliable Low-Latency V2X Communications

Future 6G-enabled vehicular networks face the challenge of ensuring ultra-reliable low-latency communication (URLLC) for delivering safety-critical information in a timely manner. Existing resource allocation schemes for vehicle-to-everything (V2X) communication systems primarily rely on traditional optimization-based algorithms. However, these methods often fail to guarantee the strict reliability and latency requirements of URLLC applications in dynamic vehicular environments due to the high complexity and communication overhead of the solution methodologies. This paper proposes a novel deep reinforcement learning (DRL) based framework for the joint power and block length allocation to minimize the worst-case decoding-error probability in the finite block length (FBL) regime for a URLLC-based downlink V2X communication system. The problem is formulated as a non-convex mixed-integer nonlinear programming problem (MINLP). Initially, an algorithm grounded in optimization theory is developed based on deriving the joint convexity of the decoding error probability in the block length and transmit power variables within the region of interest. Subsequently, an efficient event-triggered DRL-based algorithm is proposed to solve the joint optimization problem. Incorporating event-triggered learning into the DRL framework enables assessing whether to initiate the DRL process, thereby reducing the number of DRL process executions while maintaining reasonable reliability performance. Simulation results demonstrate that the proposed event-triggered DRL scheme can achieve 95% of the performance of the joint optimization scheme while reducing the DRL executions by up to 24% for different network settings.

arXiv:2407.11563

Green Resource Allocation in Cloud-Native O-RAN Enabled Small Cell Networks

In the rapidly evolving landscape of 5G and beyond, cloud-native Open Radio Access Networks (O-RAN) present a paradigm shift towards intelligent, flexible, and sustainable network operations. This study addresses the intricate challenge of energy efficient (EE) resource allocation that services both enhanced Mobile Broadband (eMBB) and ultra-reliable low-latency communications (URLLC) users. We propose a novel distributed learning framework leveraging on-policy and off-policy transfer learning strategies within a deep reinforcement learning (DRL)--based model to facilitate online resource allocation decisions under different channel conditions. The simulation results explain the efficacy of the proposed method, which rapidly adapts to dynamic network states, thereby achieving a green resource allocation.

arXiv:2407.11558

DRL-based Joint Resource Scheduling of eMBB and URLLC in O-RAN

This work addresses resource allocation challenges in multi-cell wireless systems catering to enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low Latency Communications (URLLC) users. We present a distributed learning framework tailored to O-RAN network architectures. Leveraging a Thompson sampling-based Deep Reinforcement Learning (DRL) algorithm, our approach provides real-time resource allocation decisions, aligning with evolving network structures. The proposed approach facilitates online decision-making for resource allocation by deploying trained execution agents at Near-Real Time Radio Access Network Intelligent Controllers (Near-RT RICs) located at network edges. Simulation results demonstrate the algorithm's effectiveness in meeting Quality of Service (QoS) requirements for both eMBB and URLLC users, offering insights into optimising resource utilisation in dynamic wireless environments.

arXiv:2407.11047

An open source Multi-Agent Deep Reinforcement Learning Routing Simulator for satellite networks

This paper introduces an open source simulator for packet routing in Low Earth Orbit Satellite Constellations (LSatCs) considering the dynamic system uncertainties. The simulator, implemented in Python, supports traditional Dijkstra's based routing as well as more advanced learning solutions, specifically Q-Routing and Multi-Agent Deep Reinforcement Learning (MA-DRL) from our previous work. It uses an event-based approach with the SimPy module to accurately simulate packet creation, routing and queuing, providing real-time tracking of queues and latency. The simulator is highly configurable, allowing adjustments in routing policies, traffic, ground and space layer topologies, communication parameters, and learning hyperparameters. Key features include the ability to visualize system motion and track packet paths. Results highlight significant improvements in end-to-end (E2E) latency using Reinforcement Learning (RL)-based routing policies compared to traditional methods. The source code, the documentation and a Jupyter notebook with post-processing results and analysis are available on GitHub.

arXiv:2407.11036

Hybrid-Generative Diffusion Models for Attack-Oriented Twin Migration in Vehicular Metaverses

The vehicular metaverse is envisioned as a blended immersive domain that promises to bring revolutionary changes to the automotive industry. As a core component of vehicular metaverses, Vehicle Twins (VTs) are digital twins that cover the entire life cycle of vehicles, providing immersive virtual services for Vehicular Metaverse Users (VMUs). Vehicles with limited resources offload the computationally intensive tasks of constructing and updating VTs to edge servers and migrate VTs between these servers, ensuring seamless and immersive experiences for VMUs. However, the high mobility of vehicles, uneven deployment of edge servers, and potential security threats pose challenges to achieving efficient and reliable VT migrations. To address these issues, we propose a secure and reliable VT migration framework in vehicular metaverses. Specifically, we design a two-layer trust evaluation model to comprehensively evaluate the reputation value of edge servers in the network communication and interaction layers. Then, we model the VT migration problem as a partially observable Markov decision process and design a hybrid-Generative Diffusion Model (GDM) algorithm based on deep reinforcement learning to generate optimal migration decisions by taking hybrid actions (i.e., continuous actions and discrete actions). Numerical results demonstrate that the hybrid-GDM algorithm outperforms the baseline algorithms, showing strong adaptability in various settings and highlighting the potential of the hybrid-GDM algorithm for addressing various optimization issues in vehicular metaverses.

arXiv:2407.13755

Random Latent Exploration for Deep Reinforcement Learning

The ability to efficiently explore high-dimensional state spaces is essential for the practical success of deep Reinforcement Learning (RL). This paper introduces a new exploration technique called Random Latent Exploration (RLE), that combines the strengths of bonus-based and noise-based (two popular approaches for effective exploration in deep RL) exploration strategies. RLE leverages the idea of perturbing rewards by adding structured random rewards to the original task rewards in certain (random) states of the environment, to encourage the agent to explore the environment during training. RLE is straightforward to implement and performs well in practice. To demonstrate the practical effectiveness of RLE, we evaluate it on the challenging Atari and IsaacGym benchmarks and show that RLE exhibits higher overall scores across all the tasks than other approaches.

arXiv:2407.13513공식 코드 · Papers with Code

Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization

Dynamic Algorithm Configuration (DAC) addresses the challenge of dynamically setting hyperparameters of an algorithm for a diverse set of instances rather than focusing solely on individual tasks. Agents trained with Deep Reinforcement Learning (RL) offer a pathway to solve such settings. However, the limited generalization performance of these agents has significantly hindered the application in DAC. Our hypothesis is that a potential bias in the training instances limits generalization capabilities. We take a step towards mitigating this by selecting a representative subset of training instances to overcome overrepresentation and then retraining the agent on this subset to improve its generalization performance. For constructing the meta-features for the subset selection, we particularly account for the dynamic nature of the RL agent by computing time series features on trajectories of actions and rewards generated by the agent's interaction with the environment. Through empirical evaluations on the Sigmoid and CMA-ES benchmarks from the standard benchmark library for DAC, called DACBench, we discuss the potentials of our selection technique compared to training on the entire instance set. Our results highlight the efficacy of instance selection in refining DAC policies for diverse instance spaces.