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

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.

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。

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.

多机构增强学习（MARL）已成为解决分散决策问题的有用方法。近年来提出的许多突破性算法一直在稳步增长。在这项工作中，我们仔细研究了这一快速发展，重点是在合作Marl的大量研究中采用的评估方法。通过对先前工作进行详细的荟萃分析，涵盖了从2016年至2022年接受出版的75篇论文，我们引起了人们对真正进步率的质疑的令人担忧的趋势。我们在更广泛的背景下进一步考虑了这些趋势，并从单一AGENT RL文献中获得了有关类似问题的灵感，这些建议以及仍然适用于MARL的建议。将这些建议与我们分析的新见解相结合，我们提出了合作MARL的标准化绩效评估方案。我们认为，这样的标准协议，如果被广泛采用，将大大提高未来研究的有效性和信誉，使复制和可重复性更加容易，并提高该领域的能力，通过能够通过能够准确评估进度的速度进行跨不同作品的合理比较。最后，我们在我们的项目网站上公开发布荟萃分析数据，以供未来的评估研究：https：//sites.google.com/view/marl-andard-protocol

近端策略优化（PPO）是一种普遍存在的上利期内学习算法，但在多代理设置中的非政策学习算法所使用的算法明显少得多。这通常是由于认为PPO的样品效率明显低于多代理系统中的销售方法。在这项工作中，我们仔细研究了合作多代理设置中PPO的性能。我们表明，基于PPO的多代理算法在四个受欢迎的多代理测试台上取得了令人惊讶的出色表现：粒子世界环境，星际争霸多代理挑战，哈纳比挑战赛和Google Research Football，并具有最少的超参数调谐任何特定领域的算法修改或架构。重要的是，与强大的非政策方法相比，PPO通常在最终奖励和样本效率中都能取得竞争性或优越的结果。最后，通过消融研究，我们分析了对PPO的经验表现至关重要的实施和高参数因素，并就这些因素提供了具体的实用建议。我们的结果表明，在使用这些实践时，简单的基于PPO的方法在合作多代理增强学习中是强大的基线。源代码可在https://github.com/marlbenchmark/on-policy上发布。

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。

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.

多智能体增强学习（Marl）为涉及多个交互代理的问题提供了一个框架。尽管与单智能案例明显相似，但多种子体问题通常仍然努力培训和分析。在这项工作中，我们提出了一种新的策略演员 - 批评算法，它将V-Trace扩展到Marl设置。我们的算法的关键优势是它在多工人设置中的高可扩展性。为此，MA-Trace利用重要的采样作为脱策校正方法，这允许分配计算，没有影响培训质量。此外，我们的算法理论上是接地 - 我们证明了一种保证收敛的定期定理。我们在星际争霸多智能课程中广泛评估算法，是多智能代理算法的标准基准。Ma-Trace在所有任务中实现了高性能，并超过了最先进的结果。

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.

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。

在过去的十年中，多智能经纪人强化学习（Marl）已经有了重大进展，但仍存在许多挑战，例如高样本复杂性和慢趋同稳定的政策，在广泛的部署之前需要克服，这是可能的。然而，在实践中，许多现实世界的环境已经部署了用于生成策略的次优或启发式方法。一个有趣的问题是如何最好地使用这些方法作为顾问，以帮助改善多代理领域的加强学习。在本文中，我们提供了一个原则的框架，用于将动作建议纳入多代理设置中的在线次优顾问。我们描述了在非传记通用随机游戏环境中提供多种智能强化代理（海军上将）的问题，并提出了两种新的基于Q学习的算法：海军上将决策（海军DM）和海军上将 - 顾问评估（Admiral-AE） ，这使我们能够通过适当地纳入顾问（Admiral-DM）的建议来改善学习，并评估顾问（Admiral-AE）的有效性。我们从理论上分析了算法，并在一般加上随机游戏中提供了关于他们学习的定点保证。此外，广泛的实验说明了这些算法：可以在各种环境中使用，具有对其他相关基线的有利相比的性能，可以扩展到大状态行动空间，并且对来自顾问的不良建议具有稳健性。

Adequately assigning credit to actions for future outcomes based on their contributions is a long-standing open challenge in Reinforcement Learning. The assumptions of the most commonly used credit assignment method are disadvantageous in tasks where the effects of decisions are not immediately evident. Furthermore, this method can only evaluate actions that have been selected by the agent, making it highly inefficient. Still, no alternative methods have been widely adopted in the field. Hindsight Credit Assignment is a promising, but still unexplored candidate, which aims to solve the problems of both long-term and counterfactual credit assignment. In this thesis, we empirically investigate Hindsight Credit Assignment to identify its main benefits, and key points to improve. Then, we apply it to factored state representations, and in particular to state representations based on the causal structure of the environment. In this setting, we propose a variant of Hindsight Credit Assignment that effectively exploits a given causal structure. We show that our modification greatly decreases the workload of Hindsight Credit Assignment, making it more efficient and enabling it to outperform the baseline credit assignment method on various tasks. This opens the way to other methods based on given or learned causal structures.

分散的学习对合作多代理增强学习（MARL）表现出了巨大的希望。但是，非平稳性仍然是分散学习的重大挑战。在论文中，我们以最简单和基本的方式解决了非平稳性问题，并提出\ textit {多代理替代Q学习}（MA2QL），在那里，代理商轮流通过Q学习来更新其Q-函数。MA2QL是完全分散合作MARL的一种\ Textit {Minimalist}方法，但理论上是基础的。我们证明，当每个代理商在每个回合都保证$ \ varepsilon $ -Convergence时，他们的联合政策会收敛到NASH平衡。实际上，MA2QL仅需要对独立Q学习（IQL）的最小变化。我们经验评估MA2QL对各种合作的多代理任务。结果表明，MA2QL始终胜过IQL，尽管这种变化很小，但它验证了MA2QL的有效性。

Starcraft II（SC2）对强化学习（RL）提出了巨大的挑战，其中主要困难包括巨大的状态空间，不同的动作空间和长期的视野。在这项工作中，我们研究了《星际争霸II》全长游戏的一系列RL技术。我们研究了涉及提取的宏观活动和神经网络的层次结构的层次RL方法。我们研究了课程转移培训程序，并在具有4个GPU和48个CPU线的单台计算机上训练代理。在64x64地图并使用限制性单元上，我们对内置AI的获胜率达到99％。通过课程转移学习算法和战斗模型的混合物，我们在最困难的非作战水平内置AI（7级）中获得了93％的胜利率。在本文的扩展版本中，我们改进了架构，以针对作弊水平训练代理商，并在8级，9级和10级AIS上达到胜利率，为96％，97％和94 ％， 分别。我们的代码在https://github.com/liuruoze/hiernet-sc2上。为了为我们的工作以及研究和开源社区提供基线，我们将其复制了一个缩放版本的Mini-Alphastar（MAS）。 MAS的最新版本为1.07，可以在具有564个动作的原始动作空间上进行培训。它旨在通过使超参数可调节来在单个普通机器上进行训练。然后，我们使用相同的资源将我们的工作与MAS进行比较，并表明我们的方法更有效。迷你α的代码在https://github.com/liuruoze/mini-alphastar上。我们希望我们的研究能够阐明对SC2和其他大型游戏有效增强学习的未来研究。

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。

深度强化学习（RL）导致了许多最近和开创性的进步。但是，这些进步通常以培训的基础体系结构的规模增加以及用于训练它们的RL算法的复杂性提高，而均以增加规模的成本。这些增长反过来又使研究人员更难迅速原型新想法或复制已发表的RL算法。为了解决这些问题，这项工作描述了ACME，这是一个用于构建新型RL算法的框架，这些框架是专门设计的，用于启用使用简单的模块化组件构建的代理，这些组件可以在各种执行范围内使用。尽管ACME的主要目标是为算法开发提供一个框架，但第二个目标是提供重要或最先进算法的简单参考实现。这些实现既是对我们的设计决策的验证，也是对RL研究中可重复性的重要贡献。在这项工作中，我们描述了ACME内部做出的主要设计决策，并提供了有关如何使用其组件来实施各种算法的进一步详细信息。我们的实验为许多常见和最先进的算法提供了基准，并显示了如何为更大且更复杂的环境扩展这些算法。这突出了ACME的主要优点之一，即它可用于实现大型，分布式的RL算法，这些算法可以以较大的尺度运行，同时仍保持该实现的固有可读性。这项工作提出了第二篇文章的版本，恰好与模块化的增加相吻合，对离线，模仿和从演示算法学习以及作为ACME的一部分实现的各种新代理。

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.

保守主义的概念导致了离线强化学习（RL）的重要进展，其中代理从预先收集的数据集中学习。但是，尽可能多的实际方案涉及多个代理之间的交互，解决更实际的多代理设置中的离线RL仍然是一个开放的问题。鉴于最近将Online RL算法转移到多代理设置的成功，可以预期离线RL算法也将直接传输到多代理设置。令人惊讶的是，当基于保守的算法应用于多蛋白酶的算法时，性能显着降低了越来越多的药剂。为了减轻劣化，我们确定了价值函数景观可以是非凹形的关键问题，并且策略梯度改进容易出现本地最优。自从任何代理人的次优政策可能导致不协调的全球失败以来，多个代理人会加剧问题。在这种直觉之后，我们提出了一种简单而有效的方法，脱机多代理RL与演员整流（OMAR），通过有效的一阶政策梯度和Zeroth订单优化方法为演员更好地解决这一关键挑战优化保守值函数。尽管简单，奥马尔显着优于强大的基线，在多售后连续控制基准测试中具有最先进的性能。

Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to learn the model of the environment. The significant compounding error may hinder the learning process when model-based methods are applied to multi-agent tasks. This paper proposes an implicit model-based multi-agent reinforcement learning method based on value decomposition methods. Under this method, agents can interact with the learned virtual environment and evaluate the current state value according to imagined future states in the latent space, making agents have the foresight. Our approach can be applied to any multi-agent value decomposition method. The experimental results show that our method improves the sample efficiency in different partially observable Markov decision process domains.