多智能体深度强化学习研究综述

多智能体深度强化学习是机器学习领域的一个新兴的研究热点和应用方向,涵盖众多算法、规则、框架,并广泛应用于自动驾驶、能源分配、编队控制、航迹规划、路由规划、社会难题等现实领域,具有极高的研究价值和意义。对多智能体深度强化学习的基本理论、发展历程进行简要的概念介绍;按照无关联型、通信规则型、互相合作型和建模学习型4种分类方式阐述了现有的经典算法;对多智能体深度强化学习算法的实际应用进行了综述,并简单罗列了多智能体深度强化学习的现有测试平台;总结了多智能体深度强化学习在理论、算法和应用方面面临的挑战和未来的发展方向。     

基于强化学习的自适应多Agent系统的构造

自适应系统所处的环境往往是不确定的,其变化事先难以预测,如何支持这种环境下复杂自适应系统的开发已经成为软件工程领域面临的一项重要挑战.强化学习是机器学习领域中的一个重要分支,强化学习系统能够通过不断试错的方式,学习环境状态到可执行动作的最优对应策略.本文针对自适应系统环境不确定的问题,将Agent技术与强化学习技术相结...     

动态联盟收益值的再励学习

联盟形成的收益值是模糊和不确定的,难于计算,而联盟收益值在成员变化的情况下的计算就更为复杂。Lerman等人实现了动态联盟Agent进出联盟的管理方法,Chalkiadakis则研究了不确定情况下联盟的再励学习,但没有涉及联盟成员变化情况下的收益值动态性。论文定义了带折扣率的估计核,给出一种再励学习算法来计算联盟成员变化后的收益值,深化了Chalkiadakis的工作。实验结果验证了该方法的可行性和正确性。     

增强协作多智能体强化学习中的全局信用分配机制

针对协作多智能体强化学习中的全局信用分配机制很难捕捉智能体之间的复杂协作关系及无法有效地处理非马尔可夫奖励信号的问题,提出了一种增强的协作多智能体强化学习中的全局信用分配机制。首先,设计了一种新的基于奖励高速路连接的全局信用分配结构,使得智能体在决策时能够考虑其所分得的局部奖励信号与团队的全局奖励信号;其次,通过融合多步奖励信号提出了一种能够适应非马尔可夫奖励的值函数估计方法。在星际争霸微操作实验平台上的多个复杂场景下的实验结果表明:所提方法不仅能够取得先进的性能,同时还能大大提高样本的利用率。     

基于值分解的多目标多智能体深度强化学习方法

多智能体深度强化学习方法可应用于真实世界中需要多方协作的场景,是强化学习领域内的研究热点。在多目标多智能体合作场景中,各智能体之间具有复杂的合作与竞争并存的混合关系,在这些场景中应用多智能体强化学习方法时,其性能取决于该方法是否能够充分地衡量各智能体之间的关系、区分合作和竞争动作,同时也需要解决高维数据的处理以及算法效率等应用难点。针对多目标多智能体合作场景,在QMIX模型的基础上提出一种基于目标的值分解深度强化学习方法,并使用注意力机制衡量智能体之间的群体影响力,利用智能体的目标信息实现量两阶段的值分解,提升对复杂智能体关系的刻画能力,从而提高强化学习方法在多目标多智能体合作场景中的性能。实验结果表明,相比QMIX模型,该方法在星际争霸2微观操控平台上的得分与其持平,在棋盘游戏中得分平均高出4.9分,在多粒子运动环境merge和cross中得分分别平均高出25分和280.4分,且相较于主流深度强化学习方法也具有更高的得分与更好的性能表现。     

When Does Communication Learning Need Hierarchical Multi-Agent Deep Reinforcement Learning

Abstract

Multi-agent systems need to communicate to coordinate a shared task. We show that a recurrent neural network (RNN) can learn a communication protocol for coordination, even if the actions to coordinate are performed steps after the communication phase. We show that a separation of tasks with different temporal scale is necessary for successful learning. We contribute a hierarchical deep reinforcement learning model for multi-agent systems that separates the communication and coordination task from the action picking through a hierarchical policy. We further on show, that a separation of concerns in communication is beneficial but not necessary. As a testbed, we propose the Dungeon Lever Game and we extend the Differentiable Inter-Agent Learning (DIAL) framework. We present and compare results from different model variations on the Dungeon Lever Game.     

基于随机博弈的Agent协同强化学习方法

本文针对一类追求系统得益最大化的协作团队的学习问题,基于随机博弈的思想,提出了一种新的多Agent协同强化学习方法。协作团队中的每个Agent通过观察协作相识者的历史行为,依照随机博弈模型预测其行为策略,进而得出最优的联合行为策略。     

单agent强化学习与多agent强化学习比较研究

学习、交互及其结合是建立健壮、自治agent的关键必需能力。强化学习是agent学习的重要部分,agent强化学习包括单agent强化学习和多agent强化学习。文章对单agent强化学习与多agent强化学习进行了比较研究,从基本概念、环境框架、学习目标、学习算法等方面进行了对比分析,指出了它们的区别和联系,并讨论了它们所面临的一些开放性的问题。     

基于多智能体强化学习的多AGV路径规划方法

AGV(automated guided vehicle)路径规划问题已成为货物运输、快递分拣等领域中一项关键技术问题。由于在此类场景中需要较多的AGV合作完成,传统的规划模型难以协调多AGV之间的相互作用,采用分而治之的思想或许能获得系统的最优性能。基于此,该文提出一种最大回报频率的多智能体独立强化学习MRF(maximum reward frequency)Q-learning算法,对任务调度和路径规划同时进行优化。在学习阶段AGV不需要知道其他AGV的动作,减轻了联合动作引起的维数灾问题。采用Boltzmann与ε-greedy结合策略,避免收敛到较差路径,另外算法提出采用获得全局最大累积回报的频率作用于Q值更新公式,最大化多AGV的全局累积回报。仿真实验表明,该算法能够收敛到最优解,以最短的时间步长完成路径规划任务。     

A Reinforcement Learning Scheme for a Partially-Observable Multi-Agent Game

We formulate an automatic strategy acquisition problem for the multi-agent card game Hearts as a reinforcement learning problem. The problem can approximately be dealt with in the framework of a partially observable Markov decision process (POMDP) for a single-agent system. Hearts is an example of imperfect information games, which are more difficult to deal with than perfect information games. A POMDP is a decision problem that includes a process for estimating unobservable state variables. By regarding missing information as unobservable state variables, an imperfect information game can be formulated as a POMDP. However, the game of Hearts is a realistic problem that has a huge number of possible states, even when it is approximated as a single-agent system. Therefore, further approximation is necessary to make the strategy acquisition problem tractable. This article presents an approximation method based on estimating unobservable state variables and predicting the actions of the other agents. Simulation results show that our reinforcement learning method is applicable to such a difficult multi-agent problem.Editor Risto Miikkulainen     

Efficient Exploration for Multi-Agent Reinforcement Learning via Transferable Successor Features

In multi-agent reinforcement learning (MARL), the behaviors of each agent can influence the learning of others, and the agents have to search in an exponentially enlarged joint-action space. Hence, it is challenging for the multi-agent teams to explore in the environment. Agents may achieve suboptimal policies and fail to solve some complex tasks. To improve the exploring efficiency as well as the performance of MARL tasks, in this paper, we propose a new approach by transferring the knowledge across tasks. Differently from the traditional MARL algorithms, we first assume that the reward functions can be computed by linear combinations of a shared feature function and a set of task-specific weights. Then, we define a set of basic MARL tasks in the source domain and pre-train them as the basic knowledge for further use. Finally, once the weights for target tasks are available, it will be easier to get a well-performed policy to explore in the target domain. Hence, the learning process of agents for target tasks is speeded up by taking full use of the basic knowledge that was learned previously. We evaluate the proposed algorithm on two challenging MARL tasks: cooperative box-pushing and non-monotonic predator-prey. The experiment results have demonstrated the improved performance compared with state-of-the-art MARL algorithms.      

基于强化学习的多智能体协作方法研究

为了在连续和动态的环境中处理智能体不断变化的需求,我们通过利用强化学习来研究多机器人推箱子问题,得到了一种智能体可以不需要其它智能体任何信息的情况下完成协作任务的方法。强化学习可以应用于合作和非合作场合,对于存在噪声干扰和通讯困难的情况,强化学习具有其它人工智能方法不可比拟的优越性。     

一种基于角色跟踪的群体Agent再励学习算法

在多Agent系统中,通过学习可以使Agent不断增加和强化已有的知识与能力,并选择合理的动作最大化自己的利益．但目前有关Agent学习大都限于单Agent模式,或仅考虑Agent个体之间的对抗,没有考虑Agent的群体对抗,没有考虑Agent在团队中的角色,完全依赖对效用的感知来判断对手的策略,导致算法的收敛速度不高．因此,将单Agent学习推广到在非通信群体对抗环境下的群体Agent学习．考虑不同学习问题的特殊性,在学习模型中加入了角色属性,提出一种基于角色跟踪的群体Agent再励学习算法,并进行了实验分析．在学习过程中动态跟踪对手角色,并根据对手角色与其行为的匹配度动态决定学习速率,利用minmax-Q算法修正每个状态的效用值,最终加快学习的收敛速度,从而改进了Bowling和Littman等人的工作．     

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation, which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units (RSU) or unmanned aerial vehicles (UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning (MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization (MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers (e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach outperforms the MAPPO approach by around 2% and effectively reduces approximately 20% of the latency of avatar task execution in UAV-assisted vehicular Metaverses.

     

一种基于分布式强化学习的多智能体协调方法

多智能体系统研究的重点在于使功能独立的智能体通过协商、协调和协作,完成复杂的控制任务或解决复杂的问题。通过对分布式强化学习算法的研究和分析,提出了一种多智能体协调方法,协调级将复杂的系统任务进行分解,协调智能体利用中央强化学习进行子任务的分配,行为级中的任务智能体接受各自的子任务,利用独立强化学习分别选择有效的行为,协作完成系统任务。通过在Robot Soccer仿真比赛中的应用和实验,说明了基于分布式强化学习的多智能体协调方法的效果优于传统的强化学习。     

强化学习算法与应用综述

强化学习是机器学习领域的研究热点,是考察智能体与环境的相互作用,做出序列决策、优化策略并最大化累积回报的过程.强化学习具有巨大的研究价值和应用潜力,是实现通用人工智能的关键步骤.本文综述了强化学习算法与应用的研究进展和发展动态,首先介绍强化学习的基本原理,包括马尔可夫决策过程、价值函数、探索-利用问题.其次,回顾强化学习经典算法,包括基于价值函数的强化学习算法、基于策略搜索的强化学习算法、结合价值函数和策略搜索的强化学习算法,以及综述强化学习前沿研究,主要介绍多智能体强化学习和元强化学习方向.最后综述强化学习在游戏对抗、机器人控制、城市交通和商业等领域的成功应用,以及总结与展望.     

Privacy Preserving Demand Side Management Method via Multi-Agent Reinforcement Learning

The smart grid utilizes the demand side management technology to motivate energy users towards cutting demand during peak power consumption periods, which greatly improves the operation efficiency of the power grid. However, as the number of energy users participating in the smart grid continues to increase, the demand side management strategy of individual agent is greatly affected by the dynamic strategies of other agents. In addition, the existing demand side management methods, which need to obtain users’ power consumption information, seriously threaten the users’ privacy. To address the dynamic issue in the multi-microgrid demand side management model, a novel multi-agent reinforcement learning method based on centralized training and decentralized execution paradigm is presented to mitigate the damage of training performance caused by the instability of training experience. In order to protect users’ privacy, we design a neural network with fixed parameters as the encryptor to transform the users’ energy consumption information from low-dimensional to high-dimensional and theoretically prove that the proposed encryptor-based privacy preserving method will not affect the convergence property of the reinforcement learning algorithm. We verify the effectiveness of the proposed demand side management scheme with the real-world energy consumption data of Xi’an, Shaanxi, China. Simulation results show that the proposed method can effectively improve users’ satisfaction while reducing the bill payment compared with traditional reinforcement learning (RL) methods (i.e., deep Q learning (DQN), deep deterministic policy gradient (DDPG), QMIX and multi-agent deep deterministic policy gradient (MADDPG)). The results also demonstrate that the proposed privacy protection scheme can effectively protect users’ privacy while ensuring the performance of the algorithm.

     

基于动态融合目标的深度强化学习算法研究

针对深度强化学习算法中存在的过估计问题,提出了一种目标动态融合机制,在Deep [Q] Networks（DQN）算法基础上进行改进,通过融合Sarsa算法的在线更新目标,来减少DQN算法存在的过估计影响,动态地结合了DQN算法和Sarsa算法各自优点,提出了DTDQN（Dynamic Target Deep [Q] Network）算法。利用公测平台OpenAI Gym上Cart-Pole控制问题进行仿真对比实验,结果表明DTDQN算法能够有效地减少值函数过估计,具有更好的学习性能,训练稳定性有明显提升。     

基于深度强化学习的多无人机电力巡检任务规划

无人机因其成本低、操控性强等优势,在电网线路与电塔的巡检任务中取得了广泛的应用。在大范围电网巡检任务中,单台无人机由于其续航半径有限,需要多架无人机协作完成巡检任务。传统任务规划方法存在计算速度慢、协作效果不突出等问题。针对以上问题,本文提出一种基于多智能体强化学习值混合网络（QMIX）的任务规划算法,采用集中训练、分散执行的框架,为每架无人机建立循环神经网络,并通过混合网络得到联合动作值函数指导训练。该算法通过设计任务奖赏函数以激发多智能体的协作能力,有效解决多无人机任务规划协作效率低的问题。仿真实验结果表明所提算法的任务时间相比于常用的值分解网络（VDN）算法减少了350.4 s。     

基于后悔值的多Agent冲突博弈强化学习模型

对于冲突博弈,研究了一种理性保守的行为选择方法,即最小化最坏情况下Agent的后悔值.在该方法下,Agent当前的行为策略在未来可能造成的损失最小,并且在没有任何其他Agent信息的条件下,能够得到Nash均衡混合策略.基于后悔值提出了多Agent复杂环境下冲突博弈的强化学习模型以及算法实现.该模型中通过引入交叉熵距离建立信念更新过程,进一步优化了冲突博弈时的行为选择策略.基于Markov重复博弈模型验证了算法的收敛性,分析了信念与最优策略的关系.此外,与MMDP(multi-agent markov decision process)下Q学习扩展算法相比,该算法在很大程度上减少了冲突发生的次数,增强了Agent行为的协调性,并且提高了系统的性能,有利于维持系统的稳定.