Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergence

• URL: http://arxiv.org/abs/2503.14927v1
• Date: Wed, 19 Mar 2025 06:27:12 GMT
• Title: Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergence
• Authors: Yidan Wu, Yu Yu, Jianan Zhang, Li Jin,
• Abstract summary: We propose a semi-gradient, on-policy algorithm that learns an approximate optimal routing policy.<n>We demonstrate via simulations that our algorithm attains significantly faster convergence than neural network-based methods.
• Score: 7.64859175875668
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We consider the traffic control problem of dynamic routing over parallel servers, which arises in a variety of engineering systems such as transportation and data transmission. We propose a semi-gradient, on-policy algorithm that learns an approximate optimal routing policy. The algorithm uses generic basis functions with flexible weights to approximate the value function across the unbounded state space. Consequently, the training process lacks Lipschitz continuity of the gradient, boundedness of the temporal-difference error, and a prior guarantee on ergodicity, which are the standard prerequisites in existing literature on reinforcement learning theory. To address this, we combine a Lyapunov approach and an ordinary differential equation-based method to jointly characterize the behavior of traffic state and approximation weights. Our theoretical analysis proves that the training scheme guarantees traffic state stability and ensures almost surely convergence of the weights to the approximate optimum. We also demonstrate via simulations that our algorithm attains significantly faster convergence than neural network-based methods with an insignificant approximation error.

Related papers

• A Simulation-Free Deep Learning Approach to Stochastic Optimal Control [12.699529713351287]
  We propose a simulation-free algorithm for the solution of generic problems in optimal control (SOC) Unlike existing methods, our approach does not require the solution of an adjoint problem.
  arXiv  Detail & Related papers  (2024-10-07T16:16:53Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Robust Stochastically-Descending Unrolled Networks [85.6993263983062]
  Deep unrolling is an emerging learning-to-optimize method that unrolls a truncated iterative algorithm in the layers of a trainable neural network. We show that convergence guarantees and generalizability of the unrolled networks are still open theoretical problems. We numerically assess unrolled architectures trained under the proposed constraints in two different applications.
  arXiv  Detail & Related papers  (2023-12-25T18:51:23Z)
• Efficient Neural Network Approaches for Conditional Optimal Transport with Applications in Bayesian Inference [1.740133468405535]
  We present two neural network approaches that approximate the solutions of static and conditional optimal transport (COT) problems. We demonstrate both algorithms, comparing them with competing state-the-art approaches, using benchmark datasets and simulation-based inverse problems.
  arXiv  Detail & Related papers  (2023-10-25T20:20:09Z)
• Hybrid algorithm simulating non-equilibrium steady states of an open quantum system [10.752869788647802]
  Non-equilibrium steady states are a focal point of research in the study of open quantum systems. Previous variational algorithms for searching these steady states have suffered from resource-intensive implementations. We present a novel variational quantum algorithm that efficiently searches for non-equilibrium steady states by simulating the operator-sum form of the Lindblad equation.
  arXiv  Detail & Related papers  (2023-09-13T01:57:27Z)
• Efficient Bound of Lipschitz Constant for Convolutional Layers by Gram Iteration [122.51142131506639]
  We introduce a precise, fast, and differentiable upper bound for the spectral norm of convolutional layers using circulant matrix theory. We show through a comprehensive set of experiments that our approach outperforms other state-of-the-art methods in terms of precision, computational cost, and scalability. It proves highly effective for the Lipschitz regularization of convolutional neural networks, with competitive results against concurrent approaches.
  arXiv  Detail & Related papers  (2023-05-25T15:32:21Z)
• Learning to Optimize with Stochastic Dominance Constraints [103.26714928625582]
  In this paper, we develop a simple yet efficient approach for the problem of comparing uncertain quantities. We recast inner optimization in the Lagrangian as a learning problem for surrogate approximation, which bypasses apparent intractability. The proposed light-SD demonstrates superior performance on several representative problems ranging from finance to supply chain management.
  arXiv  Detail & Related papers  (2022-11-14T21:54:31Z)
• Guaranteed Conservation of Momentum for Learning Particle-based Fluid Dynamics [96.9177297872723]
  We present a novel method for guaranteeing linear momentum in learned physics simulations. We enforce conservation of momentum with a hard constraint, which we realize via antisymmetrical continuous convolutional layers. In combination, the proposed method allows us to increase the physical accuracy of the learned simulator substantially.
  arXiv  Detail & Related papers  (2022-10-12T09:12:59Z)
• Data efficient reinforcement learning and adaptive optimal perimeter control of network traffic dynamics [0.0]
  This work proposes an integral reinforcement learning (IRL) based approach to learning the macroscopic traffic dynamics for adaptive optimal perimeter control. To reduce the sampling complexity and use the available data more efficiently, the experience replay (ER) technique is introduced to the IRL algorithm. The convergence of the IRL-based algorithms and the stability of the controlled traffic dynamics are proven via the Lyapunov theory.
  arXiv  Detail & Related papers  (2022-09-13T04:28:49Z)
• LyaNet: A Lyapunov Framework for Training Neural ODEs [59.73633363494646]
  We propose a method for training ordinary differential equations by using a control-theoretic Lyapunov condition for stability. Our approach, called LyaNet, is based on a novel Lyapunov loss formulation that encourages the inference dynamics to converge quickly to the correct prediction.
  arXiv  Detail & Related papers  (2022-02-05T10:13:14Z)
• Robust Reinforcement Learning with Wasserstein Constraint [49.86490922809473]
  We show the existence of optimal robust policies, provide a sensitivity analysis for the perturbations, and then design a novel robust learning algorithm. The effectiveness of the proposed algorithm is verified in the Cart-Pole environment.
  arXiv  Detail & Related papers  (2020-06-01T13:48:59Z)
• Learning Scalable Multi-Agent Coordination by Spatial Differentiation for Traffic Signal Control [8.380832628205372]
  We design a multiagent coordination framework based on Deep Reinforcement Learning methods for traffic signal control. Specifically, we propose the Spatial Differentiation method for coordination which uses the temporal-spatial information in the replay buffer to amend the reward of each action.
  arXiv  Detail & Related papers  (2020-02-27T02:16:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.