اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدModel-Free Learning of Optimal Ergodic Policies in Wireless Systems
112
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Learning optimal resource allocation policies in wireless systems can be effectively achieved by formulating finite dimensional constrained programs which depend on system configuration, as well as the adopted learning parameterization. The interest here is in cases where system models are unavailable, prompting methods that probe the wireless system with candidate policies, and then use observed performance to determine better policies. This generic procedure is difficult because of the need to cull accurate gradient estimates out of these limited system queries. This paper constructs and exploits smoothed surrogates of constrained ergodic resource allocation problems, the gradients of the former being representable exactly as averages of finite differences that can be obtained through limited system probing. Leveraging this unique property, we develop a new model-free primal-dual algorithm for learning optimal ergodic resource allocations, while we rigorously analyze the relationships between original policy search problems and their surrogates, in both primal and dual domains. First, we show that both primal and dual domain surrogates are uniformly consistent approximations of their corresponding original finite dimensional counterparts. Upon further assuming the use of near-universal policy parameterizations, we also develop explicit bounds on the gap between optimal values of initial, infinite dimensional resource allocation problems, and dual values of their parameterized smoothed surrogates. In fact, we show that this duality gap decreases at a linear rate relative to smoothing and universality parameters. Thus, it can be made arbitrarily small at will, also justifying our proposed primal-dual algorithmic recipe. Numerical simulations confirm the effectiveness of our approach.
قيم البحث
اقرأ أيضاً
In this paper, we study the learning of safe policies in the setting of reinforcement learning problems. This is, we aim to control a Markov Decision Process (MDP) of which we do not know the transition probabilities, but we have access to sample tra
jectories through experience. We define safety as the agent remaining in a desired safe set with high probability during the operation time. We therefore consider a constrained MDP where the constraints are probabilistic. Since there is no straightforward way to optimize the policy with respect to the probabilistic constraint in a reinforcement learning framework, we propose an ergodic relaxation of the problem. The advantages of the proposed relaxation are threefold. (i) The safety guarantees are maintained in the case of episodic tasks and they are kept up to a given time horizon for continuing tasks. (ii) The constrained optimization problem despite its non-convexity has arbitrarily small duality gap if the parametrization of the policy is rich enough. (iii) The gradients of the Lagrangian associated with the safe-learning problem can be easily computed using standard policy gradient results and stochastic approximation tools. Leveraging these advantages, we establish that primal-dual algorithms are able to find policies that are safe and optimal. We test the proposed approach in a navigation task in a continuous domain. The numerical results show that our algorithm is capable of dynamically adapting the policy to the environment and the required safety levels.
Vehicle tracking has become one of the key applications of wireless sensor networks (WSNs) in the fields of rescue, surveillance, traffic monitoring, etc. However, the increased tracking accuracy requires more energy consumption. In this letter, a de
centralized vehicle tracking strategy is conceived for improving both tracking accuracy and energy saving, which is based on adjusting the intersection area between the fixed sensing area and the dynamic activation area. Then, two deep reinforcement learning (DRL) aided solutions are proposed relying on the dynamic selection of the activation area radius. Finally, simulation results show the superiority of our DRL aided design.
Risk-aware control, though with promise to tackle unexpected events, requires a known exact dynamical model. In this work, we propose a model-free framework to learn a risk-aware controller with a focus on the linear system. We formulate it as a disc
rete-time infinite-horizon LQR problem with a state predictive variance constraint. To solve it, we parameterize the policy with a feedback gain pair and leverage primal-dual methods to optimize it by solely using data. We first study the optimization landscape of the Lagrangian function and establish the strong duality in spite of its non-convex nature. Alongside, we find that the Lagrangian function enjoys an important local gradient dominance property, which is then exploited to develop a convergent random search algorithm to learn the dual function. Furthermore, we propose a primal-dual algorithm with global convergence to learn the optimal policy-multiplier pair. Finally, we validate our results via simulations.
State estimation is critical to control systems, especially when the states cannot be directly measured. This paper presents an approximate optimal filter, which enables to use policy iteration technique to obtain the steady-state gain in linear Gaus
sian time-invariant systems. This design transforms the optimal filtering problem with minimum mean square error into an optimal control problem, called Approximate Optimal Filtering (AOF) problem. The equivalence holds given certain conditions about initial state distributions and policy formats, in which the system state is the estimation error, control input is the filter gain, and control objective function is the accumulated estimation error. We present a policy iteration algorithm to solve the AOF problem in steady-state. A classic vehicle state estimation problem finally evaluates the approximate filter. The results show that the policy converges to the steady-state Kalman gain, and its accuracy is within 2 %.
Unmanned aerial vehicles (UAVs) have emerged as a promising candidate solution for data collection of large-scale wireless sensor networks (WSNs). In this paper, we investigate a UAV-aided WSN, where cluster heads (CHs) receive data from their member
nodes, and a UAV is dispatched to collect data from CHs along the planned trajectory. We aim to minimize the total energy consumption of the UAV-WSN system in a complete round of data collection. Toward this end, we formulate the energy consumption minimization problem as a constrained combinatorial optimization problem by jointly selecting CHs from nodes within clusters and planning the UAVs visiting order to the selected CHs. The formulated energy consumption minimization problem is NP-hard, and hence, hard to solve optimally. In order to tackle this challenge, we propose a novel deep reinforcement learning (DRL) technique, pointer network-A* (Ptr-A*), which can efficiently learn from experiences the UAV trajectory policy for minimizing the energy consumption. The UAVs start point and the WSN with a set of pre-determined clusters are fed into the Ptr-A*, and the Ptr-A* outputs a group of CHs and the visiting order to these CHs, i.e., the UAVs trajectory. The parameters of the Ptr-A* are trained on small-scale clusters problem instances for faster training by using the actor-critic algorithm in an unsupervised manner. At inference, three search strategies are also proposed to improve the quality of solutions. Simulation results show that the trained models based on 20-clusters and 40-clusters have a good generalization ability to solve the UAVs trajectory planning problem in WSNs with different numbers of clusters, without the need to retrain the models. Furthermore, the results show that our proposed DRL algorithm outperforms two baseline techniques.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
