Due to the scarcity in the wireless spectrum and limited energy resources especially in mobile applications, efficient resource allocation strategies are critical in wireless networks. Motivated by the recent advances in deep reinforcement learning (DRL), we address multi-agent DRL-based joint dynamic channel access and power control in a wireless interference network. We first propose a multi-agent DRL algorithm with centralized training (DRL-CT) to tackle the joint resource allocation problem. In this case, the training is performed at the central unit (CU) and after training, the users make autonomous decisions on their transmission strategies with only local information. We demonstrate that with limited information exchange and faster convergence, DRL-CT algorithm can achieve 90% of the performance achieved by the combination of weighted minimum mean square error (WMMSE) algorithm for power control and exhaustive search for dynamic channel access. In the second part of this paper, we consider distributed multi-agent DRL scenario in which each user conducts its own training and makes its decisions individually, acting as a DRL agent. Finally, as a compromise between centralized and fully distributed scenarios, we consider federated DRL (FDRL) to approach the performance of DRL-CT with the use of a central unit in training while limiting the information exchange and preserving privacy of the users in the wireless system. Via simulation results, we show that proposed learning frameworks lead to efficient adaptive channel access and power control policies in dynamic environments.
相關內容
We study a new two-time-scale stochastic gradient method for solving optimization problems, where the gradients are computed with the aid of an auxiliary variable under samples generated by time-varying Markov random processes parameterized by the underlying optimization variable. These time-varying samples make gradient directions in our update biased and dependent, which can potentially lead to the divergence of the iterates. In our two-time-scale approach, one scale is to estimate the true gradient from these samples, which is then used to update the estimate of the optimal solution. While these two iterates are implemented simultaneously, the former is updated "faster" (using bigger step sizes) than the latter (using smaller step sizes). Our first contribution is to characterize the finite-time complexity of the proposed two-time-scale stochastic gradient method. In particular, we provide explicit formulas for the convergence rates of this method under different structural assumptions, namely, strong convexity, convexity, the Polyak-Lojasiewicz condition, and general non-convexity. We apply our framework to two problems in control and reinforcement learning. First, we look at the standard online actor-critic algorithm over finite state and action spaces and derive a convergence rate of O(k^(-2/5)), which recovers the best known rate derived specifically for this problem. Second, we study an online actor-critic algorithm for the linear-quadratic regulator and show that a convergence rate of O(k^(-2/3)) is achieved. This is the first time such a result is known in the literature. Finally, we support our theoretical analysis with numerical simulations where the convergence rates are visualized.
Recently, model-based agents have achieved better performance compared with model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is very difficult to learn the model of the environment. When model-based methods are applied to multi-agent tasks, the significant compounding error may hinder the learning process. In this paper, we propose an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states, which makes agents have foresight. Our method can be applied to any multi-agent value decomposition method. The experimental results show that our method improves the sample efficiency in partially observable Markov decision process domains.
The advancements in peer-to-peer wireless power transfer (P2P-WPT) have empowered the portable and mobile devices to wirelessly replenish their battery by directly interacting with other nearby devices. The existing works unrealistically assume the users to exchange energy with any of the users and at every such opportunity. However, due to the users' mobility, the inter-node meetings in such opportunistic mobile networks vary, and P2P energy exchange in such scenarios remains uncertain. Additionally, the social interests and interactions of the users influence their mobility as well as the energy exchange between them. The existing P2P-WPT methods did not consider the joint problem for energy exchange due to user's inevitable mobility, and the influence of sociality on the latter. As a result of computing with imprecise information, the energy balance achieved by these works at a slower rate as well as impaired by energy loss for the crowd. Motivated by this problem scenario, in this work, we present a wireless crowd charging method, namely MoSaBa, which leverages mobility prediction and social information for improved energy balancing. MoSaBa incorporates two dimensions of social information, namely social context and social relationships, as additional features for predicting contact opportunities. In this method, we explore the different pairs of peers such that the energy balancing is achieved at a faster rate as well as the energy balance quality improves in terms of maintaining low energy loss for the crowd. We justify the peer selection method in MoSaBa by detailed performance evaluation. Compared to the existing state-of-the-art, the proposed method achieves better performance trade-offs between energy-efficiency, energy balance quality and convergence time.
Integrated and Adaptive Guidance and Control for Endoatmospheric Missiles via Reinforcement Learning
We apply a reinforcement meta-learning framework to optimize an integrated and adaptive guidance and flight control system for an air-to-air missile. The system is implemented as a policy that maps navigation system outputs directly to commanded rates of change for the missile's control surface deflections. The system induces intercept trajectories against a maneuvering target that satisfy control constraints on fin deflection angles, and path constraints on look angle and load. We test the optimized system in a six degrees-of-freedom simulator that includes a non-linear radome model and a strapdown seeker model, and demonstrate that the system adapts to both a large flight envelope and off-nominal flight conditions including perturbation of aerodynamic coefficient parameters and center of pressure locations, and flexible body dynamics. Moreover, we find that the system is robust to the parasitic attitude loop induced by radome refraction and imperfect seeker stabilization. We compare our system's performance to a longitudinal model of proportional navigation coupled with a three loop autopilot, and find that our system outperforms this benchmark by a large margin. Additional experiments investigate the impact of removing the recurrent layer from the policy and value function networks, performance with an infrared seeker, and flexible body dynamics.
The concept of federated learning (FL) was first proposed by Google in 2016. Thereafter, FL has been widely studied for the feasibility of application in various fields due to its potential to make full use of data without compromising the privacy. However, limited by the capacity of wireless data transmission, the employment of federated learning on mobile devices has been making slow progress in practical. The development and commercialization of the 5th generation (5G) mobile networks has shed some light on this. In this paper, we analyze the challenges of existing federated learning schemes for mobile devices and propose a novel cross-device federated learning framework, which utilizes the anonymous communication technology and ring signature to protect the privacy of participants while reducing the computation overhead of mobile devices participating in FL. In addition, our scheme implements a contribution-based incentive mechanism to encourage mobile users to participate in FL. We also give a case study of autonomous driving. Finally, we present the performance evaluation of the proposed scheme and discuss some open issues in federated learning.
Split learning (SL) is a collaborative learning framework, which can train an artificial intelligence (AI) model between a device and an edge server by splitting the AI model into a device-side model and a server-side model at a cut layer. The existing SL approach conducts the training process sequentially across devices, which incurs significant training latency especially when the number of devices is large. In this paper, we design a novel SL scheme to reduce the training latency, named Cluster-based Parallel SL (CPSL) which conducts model training in a "first-parallel-then-sequential" manner. Specifically, the CPSL is to partition devices into several clusters, parallelly train device-side models in each cluster and aggregate them, and then sequentially train the whole AI model across clusters, thereby parallelizing the training process and reducing training latency. Furthermore, we propose a resource management algorithm to minimize the training latency of CPSL considering device heterogeneity and network dynamics in wireless networks. This is achieved by stochastically optimizing the cut layer selection, real-time device clustering, and radio spectrum allocation. The proposed two-timescale algorithm can jointly make the cut layer selection decision in a large timescale and device clustering and radio spectrum allocation decisions in a small timescale. Extensive simulation results on non-independent and identically distributed data demonstrate that the proposed solutions can greatly reduce the training latency as compared with the existing SL benchmarks, while adapting to network dynamics.
Recommender systems have been widely applied in different real-life scenarios to help us find useful information. Recently, Reinforcement Learning (RL) based recommender systems have become an emerging research topic. It often surpasses traditional recommendation models even most deep learning-based methods, owing to its interactive nature and autonomous learning ability. Nevertheless, there are various challenges of RL when applying in recommender systems. Toward this end, we firstly provide a thorough overview, comparisons, and summarization of RL approaches for five typical recommendation scenarios, following three main categories of RL: value-function, policy search, and Actor-Critic. Then, we systematically analyze the challenges and relevant solutions on the basis of existing literature. Finally, under discussion for open issues of RL and its limitations of recommendation, we highlight some potential research directions in this field.
This paper surveys the field of transfer learning in the problem setting of Reinforcement Learning (RL). RL has been the key solution to sequential decision-making problems. Along with the fast advance of RL in various domains. including robotics and game-playing, transfer learning arises as an important technique to assist RL by leveraging and transferring external expertise to boost the learning process. In this survey, we review the central issues of transfer learning in the RL domain, providing a systematic categorization of its state-of-the-art techniques. We analyze their goals, methodologies, applications, and the RL frameworks under which these transfer learning techniques would be approachable. We discuss the relationship between transfer learning and other relevant topics from an RL perspective and also explore the potential challenges as well as future development directions for transfer learning in RL.
In this paper, we propose a deep reinforcement learning framework called GCOMB to learn algorithms that can solve combinatorial problems over large graphs. GCOMB mimics the greedy algorithm in the original problem and incrementally constructs a solution. The proposed framework utilizes Graph Convolutional Network (GCN) to generate node embeddings that predicts the potential nodes in the solution set from the entire node set. These embeddings enable an efficient training process to learn the greedy policy via Q-learning. Through extensive evaluation on several real and synthetic datasets containing up to a million nodes, we establish that GCOMB is up to 41% better than the state of the art, up to seven times faster than the greedy algorithm, robust and scalable to large dynamic networks.
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191