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.

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.

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。

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.

The availability of challenging benchmarks has played a key role in the recent progress of machine learning. In cooperative multi-agent reinforcement learning, the StarCraft Multi-Agent Challenge (SMAC) has become a popular testbed for centralised training with decentralised execution. However, after years of sustained improvement on SMAC, algorithms now achieve near-perfect performance. In this work, we conduct new analysis demonstrating that SMAC is not sufficiently stochastic to require complex closed-loop policies. In particular, we show that an open-loop policy conditioned only on the timestep can achieve non-trivial win rates for many SMAC scenarios. To address this limitation, we introduce SMACv2, a new version of the benchmark where scenarios are procedurally generated and require agents to generalise to previously unseen settings (from the same distribution) during evaluation. We show that these changes ensure the benchmark requires the use of closed-loop policies. We evaluate state-of-the-art algorithms on SMACv2 and show that it presents significant challenges not present in the original benchmark. Our analysis illustrates that SMACv2 addresses the discovered deficiencies of SMAC and can help benchmark the next generation of MARL methods. Videos of training are available at https://sites.google.com/view/smacv2

We explore value-based solutions for multi-agent reinforcement learning (MARL) tasks in the centralized training with decentralized execution (CTDE) regime popularized recently. However, VDN and QMIX are representative examples that use the idea of factorization of the joint actionvalue function into individual ones for decentralized execution. VDN and QMIX address only a fraction of factorizable MARL tasks due to their structural constraint in factorization such as additivity and monotonicity. In this paper, we propose a new factorization method for MARL, QTRAN, which is free from such structural constraints and takes on a new approach to transforming the original joint action-value function into an easily factorizable one, with the same optimal actions. QTRAN guarantees more general factorization than VDN or QMIX, thus covering a much wider class of MARL tasks than does previous methods. Our experiments for the tasks of multi-domain Gaussian-squeeze and modified predator-prey demonstrate QTRAN's superior performance with especially larger margins in games whose payoffs penalize non-cooperative behavior more aggressively.

In this paper, we identify the best learning scenario to train a team of agents to compete against multiple possible strategies of opposing teams. We evaluate cooperative value-based methods in a mixed cooperative-competitive environment. We restrict ourselves to the case of a symmetric, partially observable, two-team Markov game. We selected three training methods based on the centralised training and decentralised execution (CTDE) paradigm: QMIX, MAVEN and QVMix. For each method, we considered three learning scenarios differentiated by the variety of team policies encountered during training. For our experiments, we modified the StarCraft Multi-Agent Challenge environment to create competitive environments where both teams could learn and compete simultaneously. Our results suggest that training against multiple evolving strategies achieves the best results when, for scoring their performances, teams are faced with several strategies.

多代理深度增强学习（Marl）缺乏缺乏共同使用的评估任务和标准，使方法之间的比较困难。在这项工作中，我们提供了一个系统评估，并比较了三种不同类别的Marl算法（独立学习，集中式多代理政策梯度，价值分解）在各种协作多智能经纪人学习任务中。我们的实验是在不同学习任务中作为算法的预期性能的参考，我们为不同学习方法的有效性提供了见解。我们开源EPYMARL，它将Pymarl CodeBase扩展到包括其他算法，并允许灵活地配置算法实现细节，例如参数共享。最后，我们开源两种环境，用于多智能经纪研究，重点关注稀疏奖励下的协调。

在本文中，我们提出了一个名为“星际争霸多代理挑战”的新颖基准，代理商学习执行多阶段任务并使用没有精确奖励功能的环境因素。以前的挑战（SMAC）被认为是多名强化学习的标准基准，主要涉及确保所有代理人仅通过具有明显的奖励功能的精细操纵而合作消除接近对手。另一方面，这一挑战对MARL算法的探索能力有效地学习隐式多阶段任务和环境因素以及微控制感兴趣。这项研究涵盖了进攻和防御性场景。在进攻情况下，代理商必须学会先寻找对手，然后消除他们。防御性场景要求代理使用地形特征。例如，代理需要将自己定位在保护结构后面，以使敌人更难攻击。我们研究了SMAC+下的MARL算法，并观察到最近的方法在与以前的挑战类似，但在进攻情况下表现不佳。此外，我们观察到，增强的探索方法对性能有积极影响，但无法完全解决所有情况。这项研究提出了未来研究的新方向。

多代理增强学习（MARL）最近在各个领域取得了巨大的成功。但是，借助黑盒神经网络架构，现有的MARL方法以不透明的方式做出决策，使人无法理解学习知识以及输入观察如何影响决策。我们的解决方案是混合经常性的软决策树（MixRTS），这是一种可解释的新型结构，可以通过决策树的根到叶子路径来表示明确的决策过程。我们在软决策树中引入了一种新颖的经常性结构，以解决部分观察性，并通过仅基于局部观察结果线性混合复发树的输出来估算关节作用值。理论分析表明，混合物在分解中保证具有添加性和单调性的结构约束。我们在一系列具有挑战性的Starcraft II任务上评估MixRT。实验结果表明，与广泛研究的基线相比，我们的可解释的学习框架获得了竞争性能，并提供了对决策过程的更直接的解释和领域知识。

多代理游戏中的均衡选择是指选择帕累托最佳平衡的问题。已经表明，由于每个代理商在训练过程中对其他代理商的政策的不确定性，许多最先进的多机构增强学习（MARL）算法容易融合到帕累托主导的平衡。为了解决次优的平衡选择，我们提出了一种使用无关紧要游戏的简单原则（具有相同奖励的超级合作游戏）的参与者批评算法（PAC）：每个代理人都可以假设其他人会选择动作的动作这将导致帕累托最佳平衡。我们评估了PAC在一系列多种多样的游戏中，并表明与替代MARL算法相比，它会收敛到更高的情节回报，并在一系列矩阵游戏中成功收敛到帕累托优势。最后，我们提出了一个图形神经网络扩展，该扩展可以在具有多达15个代理商的游戏中有效地扩展。

通过集中培训和分散执行的价值功能分解是有助于解决合作多功能协商强化任务的承诺。该地区QMIX的方法之一已成为最先进的，在星际争霸II微型管理基准上实现了最佳性能。然而，已知QMIX中每个代理估计的单调混合是限制它可以表示的关节动作Q值，以及单个代理价值函数估计的全局状态信息，通常导致子优相。为此，我们呈现LSF-SAC，这是一种新颖的框架，其具有基于变分推理的信息共享机制，作为额外的状态信息，以帮助在价值函数分子中提供各个代理。我们证明，这种潜在的个人状态信息共享可以显着扩展价值函数分解的力量，而通过软演员批评设计仍然可以在LSF-SAC中保持完全分散的执行。我们在星际争霸II微型管理挑战上评估LSF-SAC，并证明它在挑战协作任务方面优于几种最先进的方法。我们进一步设定了广泛的消融研究，以定位核算其绩效改进的关键因素。我们认为，这种新的洞察力可以导致新的地方价值估算方法和变分的深度学习算法。可以在https://sites.google.com/view/sacmm处找到演示视频和实现代码。

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。

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate endto-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL). The former uses deep Q-learning, while the latter exploits the fact that, during learning, agents can backpropagate error derivatives through (noisy) communication channels. Hence, this approach uses centralised learning but decentralised execution. Our experiments introduce new environments for studying the learning of communication protocols and present a set of engineering innovations that are essential for success in these domains.

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.

在本文中，我们认为合作的多代理强化学习（MARL）具有稀疏的奖励。为了解决这个问题，我们提出了一种名为Maser：MARL的新方法，并具有从经验重播缓冲区产生的子目标。在广泛使用的集中式培训的假设下，通过分散执行和对MARL的Q值分解的一致性，Maser通过考虑单个Q值和总Q值来自动为多个代理人生成适当的子目标。然后，Maser根据与Q学习相关的可行表示为每个代理设计个人固有奖励，以便代理人达到其子目标，同时最大化联合行动值。数值结果表明，与其他最先进的MARL算法相比，Maser的表现明显优于Starcraft II微管理基准。

Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinforcement learning, then progress to the main streams of value-based and policybased methods. Our survey will cover central algorithms in deep reinforcement learning, including the deep Q-network, trust region policy optimisation, and asynchronous advantage actor-critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via reinforcement learning. To conclude, we describe several current areas of research within the field.

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。

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。

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.