We posit a new mechanism for cooperation in multi-agent reinforcement learning (MARL) based upon any nonlinear function of the team's long-term state-action occupancy measure, i.e., a \emph{general utility}. This subsumes the cumulative return but also allows one to incorporate risk-sensitivity, exploration, and priors. % We derive the {\bf D}ecentralized {\bf S}hadow Reward {\bf A}ctor-{\bf C}ritic (DSAC) in which agents alternate between policy evaluation (critic), weighted averaging with neighbors (information mixing), and local gradient updates for their policy parameters (actor). DSAC augments the classic critic step by requiring agents to (i) estimate their local occupancy measure in order to (ii) estimate the derivative of the local utility with respect to their occupancy measure, i.e., the "shadow reward". DSAC converges to $ε$-stationarity in $\mathcal{O}(1/ε^{2.5})$ (Theorem \ref{theorem:final}) or faster $\mathcal{O}(1/ε^{2})$ (Corollary \ref{corollary:communication}) steps with high probability, depending on the amount of communications. We further establish the non-existence of spurious stationary points for this problem, that is, DSAC finds the globally optimal policy (Corollary \ref{corollary:global}). Experiments demonstrate the merits of goals beyond the cumulative return in cooperative MARL.
University of Oxford（牛津大学）；Delft University of Technology（代尔夫特理工大学）
VDN and QMIX are two popular value-based algorithms for cooperative MARL that learn a centralized action value function as a monotonic mixing of per-agent utilities. While this enables easy decentralization of the learned policy, the restricted joint action value function can prevent them from solving tasks that require significant coordination between agents at a given timestep. We show that this problem can be overcome by improving the joint exploration of all agents during training. Specifically, we propose a novel MARL approach called Universal Value Exploration (UneVEn) that learns a set …
Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields. An effective way to further empower these methodologies is to develop libraries and tools that could expand their interpretability and explainability. In this work, we introduce MARLeME: a MARL model extraction library, designed to improve explainability of MARL systems by approximating them with symbolic models. Symbolic models offer a high degree of interpretability, well-defined properties, and verifiable behaviour. Consequently, they can be used to inspe…
Entropy regularization is a popular method in reinforcement learning (RL). Although it has many advantages, it alters the RL objective of the original Markov Decision Process (MDP). Though divergence regularization has been proposed to settle this problem, it cannot be trivially applied to cooperative multi-agent reinforcement learning (MARL). In this paper, we investigate divergence regularization in cooperative MARL and propose a novel off-policy cooperative MARL framework, divergence-regularized multi-agent actor-critic (DMAC). Theoretically, we derive the update rule of DMAC which is natur…
Dynamic one-time delivery of critical data by small and sparse UAV swarms: a model problem for MARL scaling studies
Swedish Defence Research Agency (FOI)（瑞典国防研究机构（FOI））；Chalmers University of Technology（查尔姆斯理工大学）；the University of Gothenburg, Department of Mathematical Sciences（哥德堡大学数学科学系）
We study two state-of-the-art solutions to the multi-agent pickup and delivery (MAPD) problem based on different principles -- multi-agent path-finding (MAPF) and multi-agent reinforcement learning (MARL). Specifically, a recent MAPF algorithm called conflict-based search (CBS) and a current MARL algorithm called shared experience actor-critic (SEAC) are studied. While the performance of these algorithms is measured using quite different metrics in their separate lines of work, we aim to benchmark these two methods comprehensively in a simulated warehouse automation environment.
MARLIN: Soft Actor-Critic based Reinforcement Learning for Congestion Control in Real Networks
Florida Institute for Human & Machine Cognition (IHMC)（佛罗里达人机认知研究所（IHMC））；The University of West Florida (UWF)（西佛罗里达大学（UWF））；US Army Research Laboratory (ARL)（美国陆军研究实验室（ARL））
Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning
The Ohio State University, Columbus, Ohio, USA（俄亥俄州立大学）；University of Wisconsin-Whitewater, Whitewater, Wisconsin, USA（威斯康星大学-威奇托分校）；University of Colorado Boulder, Boulder, Colorado, USA（科罗拉多大学博尔德分校）
Beihang University（北京航空航天大学）；Yangzhou Collaborative Innovation Research Institute CO., LTD（扬州协同创新研究院有限公司）；No. 38 Research Institute of CETC（中国电子科技集团公司第三十八研究所）
While deep neural networks (DNNs) have strengthened the performance of cooperative multi-agent reinforcement learning (c-MARL), the agent policy can be easily perturbed by adversarial examples. Considering the safety critical applications of c-MARL, such as traffic management, power management and unmanned aerial vehicle control, it is crucial to test the robustness of c-MARL algorithm before it was deployed in reality. Existing adversarial attacks for MARL could be used for testing, but is limited to one robustness aspects (e.g., reward, state, action), while c-MARL model could be attacked fr…
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）
Deep Reinforcement Learning has made significant progress in multi-agent systems in recent years. In this review article, we have focused on presenting recent approaches on Multi-Agent Reinforcement Learning (MARL) algorithms. In particular, we have focused on five common approaches on modeling and solving cooperative multi-agent reinforcement learning problems: (I) independent learners, (II) fully observable critic, (III) value function factorization, (IV) consensus, and (IV) learn to communicate. First, we elaborate on each of these methods, possible challenges, and how these challenges were…
[Zhang, ICML 2018] provided the first decentralized actor-critic algorithm for multi-agent reinforcement learning (MARL) that offers convergence guarantees. In that work, policies are stochastic and are defined on finite action spaces. We extend those results to offer a provably-convergent decentralized actor-critic algorithm for learning deterministic policies on continuous action spaces. Deterministic policies are important in real-world settings. To handle the lack of exploration inherent in deterministic policies, we consider both off-policy and on-policy settings. We provide the expressio…
Sim2O: Efficient Offline-to-Online MARL via Joint Action Composition
Department of Computer Science and Engineering, Washington University in St. Louis（圣路易斯华盛顿大学计算机科学与工程系）；The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China（中国科学院自动化研究所复杂系统认知与决策智能重点实验室）
University of Minnesota（明尼苏达大学）；Rensselaer Polytechnic Institute（伦斯勒理工学院）；Texas A&M University（德克萨斯A&M大学）
Multi-agent reinforcement learning (MARL) has attracted much research attention recently. However, unlike its single-agent counterpart, many theoretical and algorithmic aspects of MARL have not been well-understood. In this paper, we study the emergence of coordinated behavior by autonomous agents using an actor-critic (AC) algorithm. Specifically, we propose and analyze a class of coordinated actor-critic algorithms (CAC) in which individually parametrized policies have a {\it shared} part (which is jointly optimized among all agents) and a {\it personalized} part (which is only locally optim…
Microsoft Research（微软研究院）；Beijing University of Posts and Telecommunications（北京邮电大学）；Hong Kong University of Science and Technology（香港科技大学）；Microsoft ARD Incubation Team（微软ARD孵化团队）
Multi-agent reinforcement learning (MARL) has been increasingly explored to learn the cooperative policy towards maximizing a certain global reward. Many existing studies take advantage of graph neural networks (GNN) in MARL to propagate critical collaborative information over the interaction graph, built upon inter-connected agents. Nevertheless, the vanilla GNN approach yields substantial defects in dealing with complex real-world scenarios since the generic message passing mechanism is ineffective between heterogeneous vertices and, moreover, simple message aggregation functions are incapab…
Artificial Intelligence Institute, University of South Carolina（南卡罗来纳大学人工智能研究所）
Recent success in cooperative multi-agent reinforcement learning (MARL) relies on centralized training and policy sharing. Centralized training eliminates the issue of non-stationarity MARL yet induces large communication costs, and policy sharing is empirically crucial to efficient learning in certain tasks yet lacks theoretical justification. In this paper, we formally characterize a subclass of cooperative Markov games where agents exhibit a certain form of homogeneity such that policy sharing provably incurs no suboptimality. This enables us to develop the first consensus-based decentraliz…
Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
State Key Laboratory of Complex & Critical Software Environment（复杂与关键软件环境国家重点实验室）；Beihang University（北京航空航天大学）；Zhongguancun Laboratory（中关村实验室）；Institute of Artificial Intelligence, Peking University（北京大学人工智能研究院）；Institute of data space, Hefei Comprehensive National Science Center（合肥综合国家科学中心数据空间研究院）；Nanyang Technological University（南洋理工大学）
Multiagent reinforcement learning algorithms (MARL) have been demonstrated on complex tasks that require the coordination of a team of multiple agents to complete. Existing works have focused on sharing information between agents via centralized critics to stabilize learning or through communication to increase performance, but do not generally look at how information can be shared between agents to address the curse of dimensionality in MARL. We posit that a multiagent problem can be decomposed into a multi-task problem where each agent explores a subset of the state space instead of explorin…
University College London（伦敦大学学院）；Huawei R&D U.K.（华为英国研发部）；Huawei Canada（华为加拿大公司）；Shanghai Jiao Tong University（上海交通大学）；University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute（阿尔伯塔机器智能研究所）
Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. A cornerstone of this success is the auto-curriculum framework, which shapes the learning process by continually creating new challenging tasks for agents to adapt to, thereby facilitating the acquisition of new skills. In order to extend MARL methods to real-world domains outside of video games, we envision in this blue sky paper that maintaining a diversity-aware auto-curriculum is critical for successful MARL applications. Specifically, we argue that \emph{behavioura…
MARL-FWC: Optimal Coordination of Freeway Traffic Control Measures
Cyber-Physical Systems Lab（智能物理系统实验室）；Egypt-Japan University of Science and Technology (E-JUST)（埃及-日本科学技术大学）；Faculty of Engineering (Shoubra)（工程学院（舒卜拉））；Benha University（班纳大学）；Faculty of Engineering（工程学院）；Alexandria University（亚历山大大学）
KD-MARL: Resource-Aware Knowledge Distillation in Multi-Agent Reinforcement Learning
School of Computer Science and Information Technology, Adelaide University, Australia（阿德莱德大学计算机科学与信息技术学院，澳大利亚）；School of Electrical Engineering, Computing and Mathematical Sciences, Curtin University, Australia（科廷大学电气工程、计算与数学科学学院，澳大利亚）；Systems Research Institute, Polish Academy of Sciences, Poland（波兰科学院系统研究所，波兰）
Fault-Tolerant MARL for CAVs under Observation Perturbations for Highway On-Ramp Merging
Department of Automation, Tsinghua University（自动化系，清华大学）；Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University（北京信息科学与技术国家研究中心（BNRist），清华大学）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Princeton University（普林斯顿大学）；Northwestern University（西北大学）；Tencent AI Lab（腾讯人工智能实验室）
We consider the problem of \emph{fully decentralized} multi-agent reinforcement learning (MARL), where the agents are located at the nodes of a time-varying communication network. Specifically, we assume that the reward functions of the agents might correspond to different tasks, and are only known to the corresponding agent. Moreover, each agent makes individual decisions based on both the information observed locally and the messages received from its neighbors over the network. Within this setting, the collective goal of the agents is to maximize the globally averaged return over the networ…
The complexity of multiagent reinforcement learning (MARL) in multiagent systems increases exponentially with respect to the agent number. This scalability issue prevents MARL from being applied in large-scale multiagent systems. However, one critical feature in MARL that is often neglected is that the interactions between agents are quite sparse. Without exploiting this sparsity structure, existing works aggregate information from all of the agents and thus have a high sample complexity. To address this issue, we propose an adaptive sparse attention mechanism by generalizing a sparsity-induci…
University of California, Berkeley（加州大学伯克利分校）；Tsinghua-Berkeley Shenzhen Institute（清华-伯克利深圳学院）；University of Southern California（南加州大学）
One of the challenges for multi-agent reinforcement learning (MARL) is designing efficient learning algorithms for a large system in which each agent has only limited or partial information of the entire system. While exciting progress has been made to analyze decentralized MARL with the network of agents for social networks and team video games, little is known theoretically for decentralized MARL with the network of states for modeling self-driving vehicles, ride-sharing, and data and traffic routing. This paper proposes a framework of localized training and decentralized execution to study …
Scalable Multi-Agent Reinforcement Learning for Residential Load Scheduling under Data Governance
EPFL（洛桑联邦理工学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
Towards Fault Tolerance in Multi-Agent Reinforcement Learning
Tsinghua University（清华大学）；QiYuan Lab（启元实验室）；Beijing National Research Center for Information Science and Technology (BNRist), Tsinghua University（北京信息科学与技术国家研究中心（BNRist），清华大学）
SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC
Zhejiang University（浙江大学）；University of Science and Technology of China（中国科学技术大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Polixir
Purpose of review: Recent advances in sensing, actuation, and computation have opened the door to multi-robot systems consisting of hundreds/thousands of robots, with promising applications to automated manufacturing, disaster relief, harvesting, last-mile delivery, port/airport operations, or search and rescue. The community has leveraged model-free multi-agent reinforcement learning (MARL) to devise efficient, scalable controllers for multi-robot systems (MRS). This review aims to provide an analysis of the state-of-the-art in distributed MARL for multi-robot cooperation. Recent findings: De…
