Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. Many approaches have been developed but they can be divided into three main types: centralized training and execution (CTE), centralized training for decentralized execution (CTDE), and Decentralized training and execution (DTE).
CTDE methods are the most common as they can use centralized information during training but execute in a decentralized manner -- using only information available to that agent during execution. CTDE is the only paradigm that requires a separate training phase where any available information (e.g., other agent policies, underlying states) can be used. As a result, they can be more scalable than CTE methods, do not require communication during execution, and can often perform well. CTDE fits most naturally with the cooperative case, but can be potentially applied in competitive or mixed settings depending on what information is assumed to be observed.
This text is an introduction to CTDE in cooperative MARL. It is meant to explain the setting, basic concepts, and common methods. It does not cover all work in CTDE MARL as the subarea is quite extensive. I have included work that I believe is important for understanding the main concepts in the subarea and apologize to those that I have omitted.
Peking University（北京大学）；Tencent AI Lab（腾讯人工智能实验室）；BAAI（北京智源人工智能研究院）
In cooperative multi-agent reinforcement learning (MARL), combining value decomposition with actor-critic enables agents to learn stochastic policies, which are more suitable for the partially observable environment. Given the goal of learning local policies that enable decentralized execution, agents are commonly assumed to be independent of each other, even in centralized training. However, such an assumption may prohibit agents from learning the optimal joint policy. To address this problem, we explicitly take the dependency among agents into centralized training. Although this leads to the…
University of Science and Technology of China（中国科学技术大学）；Huawei Cloud（华为云）
Due to the partial observability and communication constraints in many multi-agent reinforcement learning (MARL) tasks, centralized training with decentralized execution (CTDE) has become one of the most widely used MARL paradigms. In CTDE, centralized information is dedicated to learning the allocation of the team reward with a mixing network, while the learning of individual Q-values is usually based on local observations. The insufficient utility of global observation will degrade performance in challenging environments. To this end, this work proposes a novel Centralized Teacher with Decen…
Centralized Training for Decentralized Execution, where agents are trained offline using centralized information but execute in a decentralized manner online, has gained popularity in the multi-agent reinforcement learning community. In particular, actor-critic methods with a centralized critic and decentralized actors are a common instance of this idea. However, the implications of using a centralized critic in this context are not fully discussed and understood even though it is the standard choice of many algorithms. We therefore formally analyze centralized and decentralized critic approac…
Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?
Zhejiang University（浙江大学）；Zhejiang Provincial Engineering Research Center for Real-Time SmartTech in Urban Security Governance, School of Computer and Computing Science, Hangzhou City University（浙江省实时智慧城市治理实时智能技术工程研究中心，计算机与计算科学学院，杭州市大学）；State Key Laboratory of Blockchain and Data Security, Zhejiang University（区块链与数据安全国家重点实验室，浙江大学）；Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security（杭州高新技术区（滨江区）区块链与数据安全研究院）
University of Delaware（特拉华大学）；U.S. Army Research Laboratory（美国陆军研究实验室）
Recent multi-agent actor-critic methods have utilized centralized training with decentralized execution to address the non-stationarity of co-adapting agents. This training paradigm constrains learning to the centralized phase such that only pre-learned policies may be used during the decentralized phase, which performs poorly when agent communications are delayed, noisy, or disrupted. In this work, we propose a new system that can gracefully handle partially-observable information due to communication disruptions during decentralized execution. Our approach augments the multi-agent actor-crit…
Peking University（北京大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
Decentralized learning has shown great promise for cooperative multi-agent reinforcement learning (MARL). However, non-stationarity remains a significant challenge in fully decentralized learning. In the paper, we tackle the non-stationarity problem in the simplest and fundamental way and propose multi-agent alternate Q-learning (MA2QL), where agents take turns updating their Q-functions by Q-learning. MA2QL is a minimalist approach to fully decentralized cooperative MARL but is theoretically grounded. We prove that when each agent guarantees $\varepsilon$-convergence at each turn, their joint…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）
Learning a stable and generalizable centralized value function (CVF) is a crucial but challenging task in multi-agent reinforcement learning (MARL), as it has to deal with the issue that the joint action space increases exponentially with the number of agents in such scenarios. This paper proposes an approach, named SMIX($λ$), to address the issue using an efficient off-policy centralized training method within a flexible learner search space. As importance sampling for such off-policy training is both computationally costly and numerically unstable, we proposed to use the $λ$-return as a prox…
In order to collaborate efficiently with unknown partners in cooperative control settings, adaptation of the partners based on online experience is required. The rather general and widely applicable control setting, where each cooperation partner might strive for individual goals while the control laws and objectives of the partners are unknown, entails various challenges such as the non-stationarity of the environment, the multi-agent credit assignment problem, the alter-exploration problem and the coordination problem. We propose new, modular deep decentralized Multi-Agent Reinforcement Lear…
UM-SJTU Joint Institute, Shanghai Jiao Tong University（上海交通大学密西根学院）；Shanghai Jiao Tong University（上海交通大学）
We consider the problem of learning fair policies in (deep) cooperative multi-agent reinforcement learning (MARL). We formalize it in a principled way as the problem of optimizing a welfare function that explicitly encodes two important aspects of fairness: efficiency and equity. As a solution method, we propose a novel neural network architecture, which is composed of two sub-networks specifically designed for taking into account the two aspects of fairness. In experiments, we demonstrate the importance of the two sub-networks for fair optimization. Our overall approach is general as it can a…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Tubingen（蒂宾根大学）
The deep reinforcement learning (DRL) algorithm works brilliantly on solving various complex control tasks. This phenomenal success can be partly attributed to DRL encouraging intelligent agents to sufficiently explore the environment and collect diverse experiences during the agent training process. Therefore, exploration plays a significant role in accessing an optimal policy for DRL. Despite recent works making great progress in continuous control tasks, exploration in these tasks has remained insufficiently investigated. To explicitly encourage exploration in continuous control tasks, we p…
Deep reinforcement learning (DRL) is a booming area of artificial intelligence. Many practical applications of DRL naturally involve more than one collaborative learners, making it important to study DRL in a multi-agent context. Previous research showed that effective learning in complex multi-agent systems demands for highly coordinated environment exploration among all the participating agents. Many researchers attempted to cope with this challenge through learning centralized value functions. However, the common strategy for every agent to learn their local policies directly often fail to …
GEIRI North America（全球能源互联网研究院北美分院）；Jinhua Electric Power Company（金华电力公司）；SGCC Zhejiang Electric Power Company（国网浙江省电力公司）
Planning future operational scenarios of bulk power systems that meet security and economic constraints typically requires intensive labor efforts in performing massive simulations. To automate this process and relieve engineers' burden, a novel multi-stage control approach is presented in this paper to train centralized and decentralized reinforcement learning agents that can automatically adjust grid controllers for regulating transmission line flows at normal condition and under contingencies. The power grid flow control problem is formulated as Markov Decision Process (MDP). At stage one, …
F2A2: Flexible Fully-decentralized Approximate Actor-critic for Cooperative Multi-agent Reinforcement Learning
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳市人工智能与机器人研究院）；Tongji University（同济大学）；Shanghai Research Institute for Intelligent Autonomous Systems（上海智能自主系统研究院）；East China Normal University（华东师范大学）；Shanghai Jiao Tong University（上海交通大学）
Towards Global Optimality in Cooperative MARL with the Transformation And Distillation Framework
Washington University in St. Louis（华盛顿大学圣路易斯分校）；Institute for Interdisciplinary Information Sciences, Tsinghua University（清华大学交叉信息研究院）；Department of Computer Science and Technology, Tsinghua University（清华大学计算机科学与技术系）
Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem
School of Computer Science, Nanjing University of Posts and Telecommunications（南京邮电大学计算机科学学院）；School of Intelligent Science and Technology, Nanjing University（南京大学智能科学与技术学院）；School of Intelligent Science（南京大学智能科学学院）
Information sharing is key in building team cognition and enables coordination and cooperation. High-performing human teams also benefit from acting strategically with hierarchical levels of iterated communication and rationalizability, meaning a human agent can reason about the actions of their teammates in their decision-making. Yet, the majority of prior work in Multi-Agent Reinforcement Learning (MARL) does not support iterated rationalizability and only encourage inter-agent communication, resulting in a suboptimal equilibrium cooperation strategy. In this work, we show that reformulating…
TDC-Cache: A Trustworthy Decentralized Cooperative Caching Framework for Web3.0
School of Electronic and Optical Engineering, Nanjing University of Science and Technology（南京理工大学电子与光学工程学院）；College of Electronics and Information Engineering, Shenzhen University（深圳大学电子与信息工程学院）；National Mobile Communications Research Laboratory, Southeast University（东南大学国家移动通信研究中心）；Purple Mountain Laboratories（紫金山实验室）；School of Electrical Engineering and Telecommunications, The University of New South Wales（新南威尔士大学电子与电信工程学院）
We study a decentralized cooperative stochastic multi-armed bandit problem with $K$ arms on a network of $N$ agents. In our model, the reward distribution of each arm is the same for each agent and rewards are drawn independently across agents and time steps. In each round, each agent chooses an arm to play and subsequently sends a message to her neighbors. The goal is to minimize the overall regret of the entire network. We design a fully decentralized algorithm that uses an accelerated consensus procedure to compute (delayed) estimates of the average of rewards obtained by all the agents for…
University of Rochester（罗切斯特大学）；ETH Zurich（苏黎世联邦理工学院）；University of California, Davis（加利福尼亚大学戴维斯分校）；IBM T. J. Watson Research Center（IBM托马斯·J·沃森研究中心）；Tencent AI lab（腾讯人工智能实验室）
Most distributed machine learning systems nowadays, including TensorFlow and CNTK, are built in a centralized fashion. One bottleneck of centralized algorithms lies on high communication cost on the central node. Motivated by this, we ask, can decentralized algorithms be faster than its centralized counterpart? Although decentralized PSGD (D-PSGD) algorithms have been studied by the control community, existing analysis and theory do not show any advantage over centralized PSGD (C-PSGD) algorithms, simply assuming the application scenario where only the decentralized network is available. In th…
Decentralized Transformers with Centralized Aggregation are Sample-Efficient Multi-Agent World Models
Tsinghua University（清华大学）；Institute of Artificial Intelligence (TeleAI), China Telecom（人工智能研究所（TeleAI），中国电信）；Shanghai AI Laboratory（上海人工智能实验室）；Shanghai Jiaotong University（上海交通大学）
With privacy as a motivation, Federated Learning (FL) is an increasingly used paradigm where learning takes place collectively on edge devices, each with a cache of user-generated training examples that remain resident on the local device. These on-device training examples are gathered in situ during the course of users' interactions with their devices, and thus are highly reflective of at least part of the inference data distribution. Yet a distribution shift may still exist; the on-device training examples may lack for some data inputs expected to be encountered at inference time. This paper…
École Polytechnique Fédérale de Lausanne（洛桑联邦理工学院）
Rapid advances in data collection and processing capabilities have allowed for the use of increasingly complex models that give rise to nonconvex optimization problems. These formulations, however, can be arbitrarily difficult to solve in general, in the sense that even simply verifying that a given point is a local minimum can be NP-hard [1]. Still, some relatively simple algorithms have been shown to lead to surprisingly good empirical results in many contexts of interest. Perhaps the most prominent example is the success of the backpropagation algorithm for training neural networks. Several…
Decentralized algorithms solve multi-agent problems over a connected network, where the information can only be exchanged with the accessible neighbors. Though there exist several decentralized optimization algorithms, there are still gaps in convergence conditions and rates between decentralized and centralized algorithms. In this paper, we fill some gaps by considering two decentralized algorithms: EXTRA and NIDS. They both converge linearly with strongly convex objective functions. We will answer two questions regarding them. What are the optimal upper bounds for their stepsizes? Do decentr…
Decentralized training of deep learning models enables on-device learning over networks, as well as efficient scaling to large compute clusters. Experiments in earlier works reveal that, even in a data-center setup, decentralized training often suffers from the degradation in the quality of the model: the training and test performance of models trained in a decentralized fashion is in general worse than that of models trained in a centralized fashion, and this performance drop is impacted by parameters such as network size, communication topology and data partitioning. We identify the changing…
Federated learning (FL) enables learning from decentralized privacy-sensitive data, with computations on raw data confined to take place at edge clients. This paper introduces mixed FL, which incorporates an additional loss term calculated at the coordinating server (while maintaining FL's private data restrictions). There are numerous benefits. For example, additional datacenter data can be leveraged to jointly learn from centralized (datacenter) and decentralized (federated) training data and better match an expected inference data distribution. Mixed FL also enables offloading some intensiv…
Decentralized Machine Learning with Centralized Performance Guarantees via Gibbs Algorithms
1 Centre Inria d'Université Côte d'Azur, INRIA, Sophia Antipolis, France.；2 Laboratoire GAATI, Universit\' e de la Polyn\' e sie fran c aise, Fa`a`\= a , French Polynesia.；3 School of Electrical；Electronic Engineering, University of Sheffield, Sheffield, United Kingdom.；4 ECE Dept. Princeton University, Princeton, 08544 NJ, USA.
We design a low complexity decentralized learning algorithm to train a recently proposed large neural network in distributed processing nodes (workers). We assume the communication network between the workers is synchronized and can be modeled as a doubly-stochastic mixing matrix without having any master node. In our setup, the training data is distributed among the workers but is not shared in the training process due to privacy and security concerns. Using alternating-direction-method-of-multipliers (ADMM) along with a layerwise convex optimization approach, we propose a decentralized learn…
Degrees of Freedom in Multi-Agent Coordination: Between Centralized and Decentralized Regimes
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Wake Forest University（维克森林大学）；Shandong University（山东大学）；University of Science and Technology of China（中国科学技术大学）
Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series
Department of Biomedical Engineering, PolyU（PolyU 生物医学工程系）；School of Nursing, PolyU（PolyU 护理学院）；Yau Mathematical Sciences Center, Tsinghua University（清华大学尤太数学科学中心）
University of Rochester（罗切斯特大学）；University of Michigan（密歇根大学）；Kwai Inc（快手公司）；ETH Zurich（苏黎世联邦理工学院）；Hong Kong University of Science and Technology（香港科技大学）
Communication is a key bottleneck in distributed training. Recently, an \emph{error-compensated} compression technology was particularly designed for the \emph{centralized} learning and receives huge successes, by showing significant advantages over state-of-the-art compression based methods in saving the communication cost. Since the \emph{decentralized} training has been witnessed to be superior to the traditional \emph{centralized} training in the communication restricted scenario, therefore a natural question to ask is "how to apply the error-compensated technology to the decentralized lea…
Provable Privacy Advantages of Decentralized Federated Learning via Distributed Optimization
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；Aalborg University（奥尔堡大学）；University of Twente（特温特大学）；Netherlands Defence Academy（荷兰国防学院）；Delft University of Technology（代尔夫特理工大学）
Distributed learning techniques such as federated learning have enabled multiple workers to train machine learning models together to reduce the overall training time. However, current distributed training algorithms (centralized or decentralized) suffer from the communication bottleneck on multiple low-bandwidth workers (also on the server under the centralized architecture). Although decentralized algorithms generally have lower communication complexity than the centralized counterpart, they still suffer from the communication bottleneck for workers with low network bandwidth. To deal with t…
Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training
State Key Laboratory of Digital Intelligent Modeling and Simulation（数字智能建模与仿真国家重点实验室）；National University of Defense Technology（国防科技大学）；School of Cyber Science and Technology（网络安全科学与技术学院）；Shenzhen Campus of Sun Yat-sen University（中山大学深圳校区）
