Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent

• URL: http://arxiv.org/abs/2107.12416v4
• Date: Fri, 3 May 2024 03:56:09 GMT
• Title: Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent
• Authors: Gangshan Jing, He Bai, Jemin George, Aranya Chakrabortty, Piyush K. Sharma,
• Abstract summary: We propose a novel zeroth-order optimization algorithm for distributed reinforcement learning. It allows each agent to estimate its local gradient by cost evaluation independently, without use of any consensus protocol.
• Score: 7.6860514640178
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently introduced distributed zeroth-order optimization (ZOO) algorithms have shown their utility in distributed reinforcement learning (RL). Unfortunately, in the gradient estimation process, almost all of them require random samples with the same dimension as the global variable and/or require evaluation of the global cost function, which may induce high estimation variance for large-scale networks. In this paper, we propose a novel distributed zeroth-order algorithm by leveraging the network structure inherent in the optimization objective, which allows each agent to estimate its local gradient by local cost evaluation independently, without use of any consensus protocol. The proposed algorithm exhibits an asynchronous update scheme, and is designed for stochastic non-convex optimization with a possibly non-convex feasible domain based on the block coordinate descent method. The algorithm is later employed as a distributed model-free RL algorithm for distributed linear quadratic regulator design, where a learning graph is designed to describe the required interaction relationship among agents in distributed learning. We provide an empirical validation of the proposed algorithm to benchmark its performance on convergence rate and variance against a centralized ZOO algorithm.

Related papers

• Distributed Markov Chain Monte Carlo Sampling based on the Alternating Direction Method of Multipliers [143.6249073384419]
  In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers. We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art. In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
  arXiv  Detail & Related papers  (2024-01-29T02:08:40Z)
• Federated Conditional Stochastic Optimization [110.513884892319]
  Conditional optimization has found in a wide range of machine learning tasks, such as in-variant learning tasks, AUPRC, andAML. This paper proposes algorithms for distributed federated learning.
  arXiv  Detail & Related papers  (2023-10-04T01:47:37Z)
• Stochastic Unrolled Federated Learning [85.6993263983062]
  We introduce UnRolled Federated learning (SURF), a method that expands algorithm unrolling to federated learning. Our proposed method tackles two challenges of this expansion, namely the need to feed whole datasets to the unrolleds and the decentralized nature of federated learning.
  arXiv  Detail & Related papers  (2023-05-24T17:26:22Z)
• Distributed Cooperative Multi-Agent Reinforcement Learning with Directed Coordination Graph [18.04270684579841]
  Existing distributed cooperative multi-agent reinforcement learning (MARL) frameworks assume undirected coordination graphs and communication graphs. We propose a distributed RL algorithm where the local policy evaluations are based on local value functions.
  arXiv  Detail & Related papers  (2022-01-10T04:14:46Z)
• Distributed stochastic proximal algorithm with random reshuffling for non-smooth finite-sum optimization [28.862321453597918]
  Non-smooth finite-sum minimization is a fundamental problem in machine learning. This paper develops a distributed proximal-gradient algorithm with random reshuffling to solve the problem.
  arXiv  Detail & Related papers  (2021-11-06T07:29:55Z)
• DESTRESS: Computation-Optimal and Communication-Efficient Decentralized Nonconvex Finite-Sum Optimization [43.31016937305845]
  Internet-of-things, networked sensing, autonomous systems and federated learning call for decentralized algorithms for finite-sum optimizations. We develop DEcentralized STochastic REcurSive methodDESTRESS for non finite-sum optimization. Detailed theoretical and numerical comparisons show that DESTRESS improves upon prior decentralized algorithms.
  arXiv  Detail & Related papers  (2021-10-04T03:17:41Z)
• On Accelerating Distributed Convex Optimizations [0.0]
  This paper studies a distributed multi-agent convex optimization problem. We show that the proposed algorithm converges linearly with an improved rate of convergence than the traditional and adaptive gradient-descent methods. We demonstrate our algorithm's superior performance compared to prominent distributed algorithms for solving real logistic regression problems.
  arXiv  Detail & Related papers  (2021-08-19T13:19:54Z)
• Momentum Accelerates the Convergence of Stochastic AUPRC Maximization [80.8226518642952]
  We study optimization of areas under precision-recall curves (AUPRC), which is widely used for imbalanced tasks. We develop novel momentum methods with a better iteration of $O (1/epsilon4)$ for finding an $epsilon$stationary solution. We also design a novel family of adaptive methods with the same complexity of $O (1/epsilon4)$, which enjoy faster convergence in practice.
  arXiv  Detail & Related papers  (2021-07-02T16:21:52Z)
• FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data [59.50904660420082]
  Federated Learning (FL) has become a popular paradigm for learning from distributed data. To effectively utilize data at different devices without moving them to the cloud, algorithms such as the Federated Averaging (FedAvg) have adopted a "computation then aggregation" (CTA) model.
  arXiv  Detail & Related papers  (2020-05-22T23:07:42Z)
• A Hybrid-Order Distributed SGD Method for Non-Convex Optimization to Balance Communication Overhead, Computational Complexity, and Convergence Rate [28.167294398293297]
  We propose a method of distributed gradient descent (SGD) with low communication load and computational complexity, and still fast. To reduce the computational complexity in each iteration, the worker nodes approximate the directional derivatives with zeroth-order gradient estimation.
  arXiv  Detail & Related papers  (2020-03-27T14:02:15Z)
• A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms [67.67377846416106]
  We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We show that value-based methods such as TD($lambda$) and $Q$-Learning have update rules which are contractive in the space of distributions of functions.
  arXiv  Detail & Related papers  (2020-03-27T05:13:29Z)

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.