多智能体增强学习（MARL）使我们能够在挑战环境中创造自适应代理，即使观察结果有限。现代Marl方法迄今为止集中于发现分解价值函数。虽然这种方法已被证明是成功的，但是由此产生的方法具有复杂的网络结构。我们采取了彻底不同的方法，并建立在独立Q-Meashers的结构上。灵感来自基于影响的抽象，我们从观察开始的观察开始，即观察动作历史的紧凑型表示可以足以学习接近最佳分散的政策。将此观察与Dueling架构，我们的算法LAN相结合，表示这些策略作为单独的个性优势功能w.r.t.一个集中的评论家。这些本地优势网络仅在单个代理的本地观察操作历史记录上。代理商表示的集中值函数条件以及环境的完整状态。在执行之前将其施加的值函数用作稳定器，该稳定器协调学习并在学习期间制定DQN目标。与其他方法相比，这使LAN能够在代理的数量中独立于其集中式网络的网络参数的数量，而不会施加像单调值函数等额外约束。在评估星际争霸多功能挑战基准测试时，LAN显示最先进的性能，并在两个以前未解决的地图`和`3S5Z_VS_3S6Z'中获得超过80％的胜利，导致QPLEL的10％的提高在14层地图上的平均性能。此外，当代理的数量变大时，LAN使用比QPlex甚至Qmix的参数明显更少。因此，我们表明LAN的结构形成了一个关键改进，有助于Marl方法保持可扩展。

Starcraft II多代理挑战（SMAC）被创建为合作多代理增强学习（MARL）的具有挑战性的基准问题。 SMAC专注于星际争霸微管理的问题，并假设每个单元都由独立行动并仅具有本地信息的学习代理人单独控制；假定通过分散执行（CTDE）进行集中培训。为了在SMAC中表现良好，MARL算法必须处理多机构信贷分配和联合行动评估的双重问题。本文介绍了一种新的体系结构Transmix，这是一个基于变压器的联合行动值混合网络，与其他最先进的合作MARL解决方案相比，我们显示出高效且可扩展的。 Transmix利用变形金刚学习更丰富的混合功能的能力来结合代理的个人价值函数。它与以前的SMAC场景上的工作相当，并且在困难场景上胜过其他技术，以及被高斯噪音损坏的场景以模拟战争的雾。

独立的强化学习算法没有理论保证，用于在多代理设置中找到最佳策略。然而，在实践中，先前的作品报告了在某些域中的独立算法和其他方面的良好性能。此外，文献中缺乏对独立算法的优势和弱点的全面研究。在本文中，我们对四个Pettingzoo环境进行了独立算法的性能的实证比较，这些环境跨越了三种主要类别的多助理环境，即合作，竞争和混合。我们表明，在完全可观察的环境中，独立的算法可以在协作和竞争环境中与多代理算法进行同步。对于混合环境，我们表明通过独立算法培训的代理商学会单独执行，但未能学会与盟友合作并与敌人竞争。我们还表明，添加重复性提高了合作部分可观察环境中独立算法的学习。

This work considers the problem of learning cooperative policies in complex, partially observable domains without explicit communication. We extend three classes of single-agent deep reinforcement learning algorithms based on policy gradient, temporal-difference error, and actor-critic methods to cooperative multi-agent systems. We introduce a set of cooperative control tasks that includes tasks with discrete and continuous actions, as well as tasks that involve hundreds of agents. The three approaches are evaluated against each other using different neural architectures, training procedures, and reward structures. Using deep reinforcement learning with a curriculum learning scheme, our approach can solve problems that were previously considered intractable by most multi-agent reinforcement learning algorithms. We show that policy gradient methods tend to outperform both temporal-difference and actor-critic methods when using feed-forward neural architectures. We also show that recurrent policies, while more difficult to train, outperform feed-forward policies on our evaluation tasks.

在复杂的协调问题中，深层合作多智能经纪增强学习（Marl）的高效探索仍然依然存在挑战。在本文中，我们介绍了一种具有奇妙驱动的探索的新型情节多功能钢筋学习，称为EMC。我们利用对流行分解的MARL算法的洞察力“诱导的”个体Q值，即用于本地执行的单个实用程序功能，是本地动作观察历史的嵌入，并且可以捕获因奖励而捕获代理之间的相互作用在集中培训期间的反向化。因此，我们使用单独的Q值的预测误差作为协调勘探的内在奖励，利用集肠内存来利用探索的信息经验来提高政策培训。随着代理商的个人Q值函数的动态捕获了国家的新颖性和其他代理人的影响，我们的内在奖励可以促使对新或有前途的国家的协调探索。我们通过教学实例说明了我们的方法的优势，并展示了在星际争霸II微互动基准中挑战任务的最先进的MARL基础上的其显着优势。

In multi-agent reinforcement learning (MARL), many popular methods, such as VDN and QMIX, are susceptible to a critical multi-agent pathology known as relative overgeneralization (RO), which arises when the optimal joint action's utility falls below that of a sub-optimal joint action in cooperative tasks. RO can cause the agents to get stuck into local optima or fail to solve tasks that require significant coordination between agents within a given timestep. Recent value-based MARL algorithms such as QPLEX and WQMIX can overcome RO to some extent. However, our experimental results show that they can still fail to solve cooperative tasks that exhibit strong RO. In this work, we propose a novel approach called curriculum learning for relative overgeneralization (CURO) to better overcome RO. To solve a target task that exhibits strong RO, in CURO, we first fine-tune the reward function of the target task to generate source tasks that are tailored to the current ability of the learning agent and train the agent on these source tasks first. Then, to effectively transfer the knowledge acquired in one task to the next, we use a novel transfer learning method that combines value function transfer with buffer transfer, which enables more efficient exploration in the target task. We demonstrate that, when applied to QMIX, CURO overcomes severe RO problem and significantly improves performance, yielding state-of-the-art results in a variety of cooperative multi-agent tasks, including the challenging StarCraft II micromanagement benchmarks.

协作多代理增强学习（MARL）已在许多实际应用中广泛使用，在许多实际应用中，每个代理商都根据自己的观察做出决定。大多数主流方法在对分散的局部实用程序函数进行建模时，将每个局部观察结果视为完整的。但是，他们忽略了这样一个事实，即可以将局部观察信息进一步分为几个实体，只有一部分实体有助于建模推理。此外，不同实体的重要性可能会随着时间而变化。为了提高分散政策的性能，使用注意机制用于捕获本地信息的特征。然而，现有的注意模型依赖于密集的完全连接的图，并且无法更好地感知重要状态。为此，我们提出了一个稀疏的状态MARL（S2RL）框架，该框架利用稀疏的注意机制将无关的信息丢弃在局部观察中。通过自我注意力和稀疏注意机制估算局部效用函数，然后将其合并为标准的关节价值函数和中央评论家的辅助关节价值函数。我们将S2RL框架设计为即插即用的模块，使其足够一般，可以应用于各种方法。关于Starcraft II的广泛实验表明，S2RL可以显着提高许多最新方法的性能。

Cooperative multi-agent reinforcement learning (MARL) has made prominent progress in recent years. For training efficiency and scalability, most of the MARL algorithms make all agents share the same policy or value network. However, in many complex multi-agent tasks, different agents are expected to possess specific abilities to handle different subtasks. In those scenarios, sharing parameters indiscriminately may lead to similar behavior across all agents, which will limit the exploration efficiency and degrade the final performance. To balance the training complexity and the diversity of agent behavior, we propose a novel framework to learn dynamic subtask assignment (LDSA) in cooperative MARL. Specifically, we first introduce a subtask encoder to construct a vector representation for each subtask according to its identity. To reasonably assign agents to different subtasks, we propose an ability-based subtask selection strategy, which can dynamically group agents with similar abilities into the same subtask. In this way, agents dealing with the same subtask share their learning of specific abilities and different subtasks correspond to different specific abilities. We further introduce two regularizers to increase the representation difference between subtasks and stabilize the training by discouraging agents from frequently changing subtasks, respectively. Empirical results show that LDSA learns reasonable and effective subtask assignment for better collaboration and significantly improves the learning performance on the challenging StarCraft II micromanagement benchmark and Google Research Football.

Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation-learning abilities of deep neural networks. However, large centralized approaches quickly become infeasible as the number of agents scale, and fully decentralized approaches can miss important opportunities for information sharing and coordination. Furthermore, not all agents are equal -- in some cases, individual agents may not even have the ability to send communication to other agents or explicitly model other agents. This paper considers the case where there is a single, powerful, \emph{central agent} that can observe the entire observation space, and there are multiple, low-powered \emph{local agents} that can only receive local observations and are not able to communicate with each other. The central agent's job is to learn what message needs to be sent to different local agents based on the global observations, not by centrally solving the entire problem and sending action commands, but by determining what additional information an individual agent should receive so that it can make a better decision. In this work we present our MARL algorithm \algo, describe where it would be most applicable, and implement it in the cooperative navigation and multi-agent walker domains. Empirical results show that 1) learned communication does indeed improve system performance, 2) results generalize to heterogeneous local agents, and 3) results generalize to different reward structures.

我们呈现协调的近端策略优化（COPPO），该算法将原始近端策略优化（PPO）扩展到多功能代理设置。关键的想法在于多个代理之间的策略更新过程中的步骤大小的协调适应。当优化理论上接地的联合目标时，我们证明了政策改进的单调性，并基于一组近似推导了简化的优化目标。然后，我们解释了Coppo中的这种目标可以在代理商之间实现动态信用分配，从而减轻了代理政策的同时更新期间的高方差问题。最后，我们证明COPPO优于几种强大的基线，并且在典型的多代理设置下，包括最新的多代理PPO方法（即MAPPO），包括合作矩阵游戏和星际争霸II微管理任务。

政策梯度方法在多智能体增强学习中变得流行，但由于存在环境随机性和探索代理（即非公平性​​），它们遭受了高度的差异，这可能因信用分配难度而受到困扰。结果，需要一种方法，该方法不仅能够有效地解决上述两个问题，而且需要足够强大地解决各种任务。为此，我们提出了一种新的多代理政策梯度方法，称为强大的本地优势（ROLA）演员 - 评论家。 Rola允许每个代理人将个人动作值函数作为当地评论家，以及通过基于集中评论家的新型集中培训方法来改善环境不良。通过使用此本地批评，每个代理都计算基准，以减少对其策略梯度估计的差异，这导致含有其他代理的预期优势动作值，这些选项可以隐式提高信用分配。我们在各种基准测试中评估ROLA，并在许多最先进的多代理政策梯度算法上显示其鲁棒性和有效性。

Many real-world problems, such as network packet routing and the coordination of autonomous vehicles, are naturally modelled as cooperative multi-agent systems. There is a great need for new reinforcement learning methods that can efficiently learn decentralised policies for such systems. To this end, we propose a new multi-agent actor-critic method called counterfactual multi-agent (COMA) policy gradients. COMA uses a centralised critic to estimate the Q-function and decentralised actors to optimise the agents' policies. In addition, to address the challenges of multi-agent credit assignment, it uses a counterfactual baseline that marginalises out a single agent's action, while keeping the other agents' actions fixed. COMA also uses a critic representation that allows the counterfactual baseline to be computed efficiently in a single forward pass. We evaluate COMA in the testbed of StarCraft unit micromanagement, using a decentralised variant with significant partial observability. COMA significantly improves average performance over other multi-agent actorcritic methods in this setting, and the best performing agents are competitive with state-of-the-art centralised controllers that get access to the full state.

在合作的多代理增强学习（MARL）中，代理只能获得部分观察，有效利用本地信息至关重要。在长期观察期间，代理可以构建\ textit {意识}，使队友减轻部分可观察性问题。但是，以前的MAL方法通常忽略了对本地信息的这种利用。为了解决这个问题，我们提出了一个新颖的框架，多代理\ textit {本地信息分解，以意识到队友}（linda），代理商通过该框架学会分解本地信息并为每个队友建立意识。我们将意识模拟为随机随机变量并执行表示学习，以确保意识表示的信息，通过最大程度地提高意识与相应代理的实际轨迹之间的相互信息。 Linda对特定算法是不可知论的，可以灵活地集成到不同的MARL方法中。足够的实验表明，所提出的框架从当地的部分观察结果中学习了信息丰富的意识，以更好地协作并显着提高学习绩效，尤其是在具有挑战性的任务上。

流动性和流量的许多方案都涉及多种不同的代理，需要合作以找到共同解决方案。行为计划的最新进展使用强化学习以寻找有效和绩效行为策略。但是，随着自动驾驶汽车和车辆对X通信变得越来越成熟，只有使用单身独立代理的解决方案在道路上留下了潜在的性能增长。多代理增强学习（MARL）是一个研究领域，旨在为彼此相互作用的多种代理找到最佳解决方案。这项工作旨在将该领域的概述介绍给研究人员的自主行动能力。我们首先解释Marl并介绍重要的概念。然后，我们讨论基于Marl算法的主要范式，并概述每个范式中最先进的方法和思想。在这种背景下，我们调查了MAL在自动移动性场景中的应用程序，并概述了现有的场景和实现。

Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in singleagent settings. We present an actor-critic algorithm that trains decentralized policies in multiagent settings, using centrally computed critics that share an attention mechanism which selects relevant information for each agent at every timestep. This attention mechanism enables more effective and scalable learning in complex multiagent environments, when compared to recent approaches. Our approach is applicable not only to cooperative settings with shared rewards, but also individualized reward settings, including adversarial settings, as well as settings that do not provide global states, and it makes no assumptions about the action spaces of the agents. As such, it is flexible enough to be applied to most multi-agent learning problems.

我们开发了一个多功能辅助救援学习（MARL）方法，以了解目标跟踪的可扩展控制策略。我们的方法可以处理任意数量的追求者和目标;我们显示出现的任务，该任务包括高达1000追踪跟踪1000个目标。我们使用分散的部分可观察的马尔可夫决策过程框架来模拟追求者作为接受偏见观察（范围和轴承）的代理，了解使用固定的未知政策的目标。注意机制用于参数化代理的价值函数;这种机制允许我们处理任意数量的目标。熵 - 正规的脱助政策RL方法用于培训随机政策，我们讨论如何在追求者之间实现对冲行为，尽管有完全分散的控制执行，但仍然导致合作较弱的合作形式。我们进一步开发了一个掩蔽启发式，允许训练较少的问题，少量追求目标和在更大的问题上执行。进行彻底的仿真实验，消融研究和对现有技术算法的比较，以研究对不同数量的代理和目标性能的方法和鲁棒性的可扩展性。

多代理增强学习（MARL）在价值函数分解方法的发展中见证了重大进展。由于单调性，它可以通过最大程度地分解每个代理实用程序来优化联合动作值函数。在本文中，我们表明，在部分可观察到的MARL问题中，代理商对自己的行为的订购可能会对代表功能类施加并发约束（跨不同状态），从而在培训期间造成重大估计错误。我们解决了这一限制，并提出了PAC，PAC是一个新的框架，利用了最佳联合行动选择的反事实预测产生的辅助信息，这可以通过新颖的反事实损失通过新颖的辅助来实现价值功能分解。开发了一种基于变异推理的信息编码方法，以从估计的基线收集和编码反事实预测。为了实现分散的执行，我们还得出了受最大收入MARL框架启发的分级分配的代理策略。我们评估了有关多代理捕食者捕食者和一组Starcraft II微管理任务的PAC。经验结果表明，在所有基准上，PAC对基于最先进的价值和基于策略的多代理增强学习算法的结果得到了改善。

Recently, some challenging tasks in multi-agent systems have been solved by some hierarchical reinforcement learning methods. Inspired by the intra-level and inter-level coordination in the human nervous system, we propose a novel value decomposition framework HAVEN based on hierarchical reinforcement learning for fully cooperative multi-agent problems. To address the instability arising from the concurrent optimization of policies between various levels and agents, we introduce the dual coordination mechanism of inter-level and inter-agent strategies by designing reward functions in a two-level hierarchy. HAVEN does not require domain knowledge and pre-training, and can be applied to any value decomposition variant. Our method achieves desirable results on different decentralized partially observable Markov decision process domains and outperforms other popular multi-agent hierarchical reinforcement learning algorithms.

在合作的多代理增强学习（MARL）中，将价值​​分解与参与者 - 批评结合，使代理人能够学习随机政策，这更适合部分可观察到的环境。鉴于学习能够分散执行的本地政策的目标，通常认为代理人彼此独立，即使在集中式培训中也是如此。但是，这样的假设可能会禁止代理人学习最佳联合政策。为了解决这个问题，我们明确地将代理商之间的依赖性带入集中式培训。尽管这导致了最佳联合政策，但对于分散的执行，可能不会分解它。然而，从理论上讲，从这样的联合政策中，我们始终可以得出另一项联合政策，该政策可实现相同的最优性，但可以分解以分散的执行。为此，我们提出了多机构条件政策分解（MACPF），该政策分解（MACPF）需要进行更集中的培训，但仍可以实现分散的执行。我们在各种合作的MARL任务中验证MACPF，并证明MACPF比基线获得更好的性能或更快的收敛性。

In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or laboratory setting, where global state information is available and communication constraints are lifted. Learning joint actionvalues conditioned on extra state information is an attractive way to exploit centralised learning, but the best strategy for then extracting decentralised policies is unclear. Our solution is QMIX, a novel value-based method that can train decentralised policies in a centralised end-to-end fashion. QMIX employs a network that estimates joint action-values as a complex non-linear combination of per-agent values that condition only on local observations. We structurally enforce that the joint-action value is monotonic in the per-agent values, which allows tractable maximisation of the joint action-value in off-policy learning, and guarantees consistency between the centralised and decentralised policies. We evaluate QMIX on a challenging set of StarCraft II micromanagement tasks, and show that QMIX significantly outperforms existing value-based multi-agent reinforcement learning methods.