This paper develops an unified framework to study finite-sample convergence guarantees of a large class of value-based asynchronous reinforcement learning (RL) algorithms. We do this by first reformulating the RL algorithms as \textit{Markovian Stochastic Approximation} (SA) algorithms to solve fixed-point equations. We then develop a Lyapunov analysis and derive mean-square error bounds on the convergence of the Markovian SA. Based on this result, we establish finite-sample mean-square convergence bounds for asynchronous RL algorithms such as $Q$-learning, $n$-step TD, TD$(λ)$, and off-policy TD algorithms including V-trace. As a by-product, by analyzing the convergence bounds of $n$-step TD and TD$(λ)$, we provide theoretical insights into the bias-variance trade-off, i.e., efficiency of bootstrapping in RL. This was first posed as an open problem in (Sutton, 1999).
Google DeepMind（谷歌DeepMind）；Montreal Institute for Learning Algorithms (MILA)（蒙特利尔学习算法研究所（MILA））；University of Montreal（蒙特利尔大学）
We propose a conceptually simple and lightweight framework for deep reinforcement learning that uses asynchronous gradient descent for optimization of deep neural network controllers. We present asynchronous variants of four standard reinforcement learning algorithms and show that parallel actor-learners have a stabilizing effect on training allowing all four methods to successfully train neural network controllers. The best performing method, an asynchronous variant of actor-critic, surpasses the current state-of-the-art on the Atari domain while training for half the time on a single multi-c…
University of Science and Technology of China（中国科学技术大学）
Deep Deterministic Policy Gradient (DDPG) has been proved to be a successful reinforcement learning (RL) algorithm for continuous control tasks. However, DDPG still suffers from data insufficiency and training inefficiency, especially in computationally complex environments. In this paper, we propose Asynchronous Episodic DDPG (AE-DDPG), as an expansion of DDPG, which can achieve more effective learning with less training time required. First, we design a modified scheme for data collection in an asynchronous fashion. Generally, for asynchronous RL algorithms, sample efficiency or/and training…
Carnegie Mellon University（卡内基梅隆大学）；Massachusetts Institute of Technology（麻省理工学院）
We study optimization algorithms based on variance reduction for stochastic gradient descent (SGD). Remarkable recent progress has been made in this direction through development of algorithms like SAG, SVRG, SAGA. These algorithms have been shown to outperform SGD, both theoretically and empirically. However, asynchronous versions of these algorithms---a crucial requirement for modern large-scale applications---have not been studied. We bridge this gap by presenting a unifying framework for many variance reduction techniques. Subsequently, we propose an asynchronous algorithm grounded in our …
We introduce SLM Lab, a software framework for reproducible reinforcement learning (RL) research. SLM Lab implements a number of popular RL algorithms, provides synchronous and asynchronous parallel experiment execution, hyperparameter search, and result analysis. RL algorithms in SLM Lab are implemented in a modular way such that differences in algorithm performance can be confidently ascribed to differences between algorithms, not between implementations. In this work we present the design choices behind SLM Lab and use it to produce a comprehensive single-codebase RL algorithm benchmark. In…
JD Finance America Corporation（京东金融美国公司）；Department of Electrical & Computer Engineering, University of Pittsburgh（匹兹堡大学电气与计算机工程系）；University of Pittsburgh（匹兹堡大学）
The privacy-preserving federated learning for vertically partitioned data has shown promising results as the solution of the emerging multi-party joint modeling application, in which the data holders (such as government branches, private finance and e-business companies) collaborate throughout the learning process rather than relying on a trusted third party to hold data. However, existing federated learning algorithms for vertically partitioned data are limited to synchronous computation. To improve the efficiency when the unbalanced computation/communication resources are common among the pa…
The Chinese University of Hong Kong（香港中文大学）；Xidian University（西安电子科技大学）
Recent years have witnessed exciting progress in the study of stochastic variance reduced gradient methods (e.g., SVRG, SAGA), their accelerated variants (e.g, Katyusha) and their extensions in many different settings (e.g., online, sparse, asynchronous, distributed). Among them, accelerated methods enjoy improved convergence rates but have complex coupling structures, which makes them hard to be extended to more settings (e.g., sparse and asynchronous) due to the existence of perturbation. In this paper, we introduce a simple stochastic variance reduced algorithm (MiG), which enjoys the best-…
The need for scalable numerical solutions has motivated the development of asynchronous parallel algorithms, where a set of nodes run in parallel with little or no synchronization, thus computing with delayed information. This paper studies the convergence of the asynchronous parallel algorithm ARock under potentially unbounded delays. ARock is a general asynchronous algorithm that has many applications. It parallelizes fixed-point iterations by letting a set of nodes randomly choose solution coordinates and update them in an asynchronous parallel fashion. ARock takes some recent asynchronous …
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）；Radisys India Pvt. Ltd.（瑞迪斯印度私人有限公司）
We consider stochastic optimization of a smooth non-convex loss function with a convex non-smooth regularizer. In the online setting, where a single sample of the stochastic gradient of the loss is available at every iteration, the problem can be solved using the proximal stochastic gradient descent (SGD) algorithm and its variants. However in many problems, especially those arising in communications and signal processing, information beyond the stochastic gradient may be available thanks to the structure of the loss function. Such extra-gradient information is not used by SGD, but has been sh…
IST Austria（奥地利科学技术研究所）；Czech Technical University in Prague（布拉格捷克理工大学）
Machine learning has made tremendous progress in recent years, with models matching or even surpassing humans on a series of specialized tasks. One key element behind the progress of machine learning in recent years has been the ability to train machine learning models in large-scale distributed shared-memory and message-passing environments. Many of these models are trained employing variants of stochastic gradient descent (SGD) based optimization. In this paper, we introduce a general consistency condition covering communication-reduced and asynchronous distributed SGD implementations. Our f…
Revisiting Multi-Agent Asynchronous Online Optimization with Delays: the Strongly Convex Case
Southeast University-Monash University Joint Graduate School（东南大学-墨尔本大学联合研究生院）；School of Computer Science and Engineering（计算机科学与工程学院）；School of Software Technology（软件技术学院）
Understanding the convergence performance of asynchronous stochastic gradient descent method (Async-SGD) has received increasing attention in recent years due to their foundational role in machine learning. To date, however, most of the existing works are restricted to either bounded gradient delays or convex settings. In this paper, we focus on Async-SGD and its variant Async-SGDI (which uses increasing batch size) for non-convex optimization problems with unbounded gradient delays. We prove $o(1/\sqrt{k})$ convergence rate for Async-SGD and $o(1/k)$ for Async-SGDI. Also, a unifying sufficien…
George Mason University（乔治梅森大学）；Old Dominion University（奥多明尼昂大学）
Energy is an essential, but often forgotten aspect in large-scale federated systems. As most of the research focuses on tackling computational and statistical heterogeneity from the machine learning algorithms, the impact on the mobile system still remains unclear. In this paper, we design and implement an online optimization framework by connecting asynchronous execution of federated training with application co-running to minimize energy consumption on battery-powered mobile devices. From a series of experiments, we find that co-running the training process in the background with foreground …
Nonconvex and nonsmooth problems have recently attracted considerable attention in machine learning. However, developing efficient methods for the nonconvex and nonsmooth optimization problems with certain performance guarantee remains a challenge. Proximal coordinate descent (PCD) has been widely used for solving optimization problems, but the knowledge of PCD methods in the nonconvex setting is very limited. On the other hand, the asynchronous proximal coordinate descent (APCD) recently have received much attention in order to solve large-scale problems. However, the accelerated variants of …
Distributed Stochastic Gradient Descent (SGD) when run in a synchronous manner, suffers from delays in waiting for the slowest learners (stragglers). Asynchronous methods can alleviate stragglers, but cause gradient staleness that can adversely affect convergence. In this work we present a novel theoretical characterization of the speed-up offered by asynchronous methods by analyzing the trade-off between the error in the trained model and the actual training runtime (wallclock time). The novelty in our work is that our runtime analysis considers random straggler delays, which helps us design …
Optimizing Asynchronous Federated Learning: A Delicate Trade-Off Between Model-Parameter Staleness and Update Frequency
EMINES, Mohammed VI Polytechnic University, Ben Guerir, Morocco（EMINES，摩洛哥穆莱·易斯大学，贝努埃里尔）；LAAS-CNRS, Université de Toulouse, CNRS, Toulouse, France（LAAS-CNRS，图卢兹大学，CNRS，图卢兹）
Regressing the vector field of a dynamical system from a finite number of observed states is a natural way to learn surrogate models for such systems. We present variants of cross-validation (Kernel Flows \cite{Owhadi19} and its variants based on Maximum Mean Discrepancy and Lyapunov exponents) as simple approaches for learning the kernel used in these emulators.
Resource Efficient Asynchronous Federated Learning for Digital Twin Empowered IoT Network
School of Electronic and Optical Engineering, Nanjing University of Science and Technology（南京理工大学电子工程与光电技术学院）；School of Information Science and Engineering, Southeast University（东南大学信息科学与工程学院）；Jiangsu Second Normal University（江苏第二师范学院）；Nanjing University of Posts and Telecommunications（南京邮电大学）；Department of Computing, The Hong Kong Polytechnic University（香港理工大学计算学系）；Department of Electronic Engineering, Shanghai Jiao Tong University（上海交通大学电子工程系）；National Mobile Communication Research Laboratory, Southeast University（东南大学国家移动通信研究实验室）
