我们分析了学习型号（如神经网络）本身是优化器时发生的学习优化的类型 - 我们将作为MESA优化的情况，我们在本文中介绍的新闻。我们认为，MESA优化的可能性为先进机器学习系统的安全和透明度提出了两个重要问题。首先，在什么情况下学习模型是优化的，包括当他们不应该？其次，当学习模型是优化器时，它的目标是什么 - 它将如何与损失函数不同，它训练的损失 - 并且如何对齐？在本文中，我们对这两个主要问题进行了深入的分析，并提供了未来研究的主题概述。

在接下来的几十年中，人工通用情报（AGI）可能会超过人类在各种重要任务下的能力。该报告为为什么如果没有实质性采取行动来阻止它，AGI可能会利用他们的智能来追求目标，而这些目标是从人类的角度出发，可能会带来潜在的灾难性后果。该报告旨在涵盖激励对对齐问题的关注的关键论点，以尽可能简洁，具体和技术上的方式进行对齐问题。我认为，现实的培训过程可能会导致AGIS中未对准的目标，尤其是因为通过强化学习训练的神经网络将学会计划实现一系列目标；通过欺骗性追求未对准的目标获得更多奖励；并以破坏服从的方式概括。就像Cotra（2022）的较早报告中一样，我在参考说明性AGI培训过程中解释了我的主张，然后概述了解决问题的不同方面的可能的研究方向。

人工智能（AI）有可能极大地改善社会，但是与任何强大的技术一样，它的风险和责任也增加。当前的AI研究缺乏有关如何管理AI系统（包括投机性长期风险）的长尾风险的系统讨论。请记住，AI可能是提高人类的长期潜力不可或缺的一部分，人们担心建立更聪明，更强大的AI系统最终可能会导致比我们更强大的系统。有人说这就像玩火，并推测这可能会造成生存风险（X风险）。为了增加这些讨论，我们回顾了来自危害分析和系统安全的时间测试概念的集合，这些概念旨在将大型流程引导到更安全的方向上。然后，我们讨论AI研究人员如何对AI系统的安全产生长期影响。最后，我们讨论如何稳健地塑造将影响安全和一般能力之间平衡的过程。

Recent progress in artificial intelligence (AI) has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn, and how they learn it. Specifically, we argue that these machines should (a) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (b) ground learning in intuitive theories of physics and psychology, to support and enrich the knowledge that is learned; and (c) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes towards these goals that can combine the strengths of recent neural network advances with more structured cognitive models.

一个令人着迷的假设是，人类和动物的智力可以通过一些原则（而不是启发式方法的百科全书清单）来解释。如果这个假设是正确的，我们可以更容易地理解自己的智能并建造智能机器。就像物理学一样，原理本身不足以预测大脑等复杂系统的行为，并且可能需要大量计算来模拟人类式的智力。这一假设将表明，研究人类和动物所剥削的归纳偏见可以帮助阐明这些原则，并为AI研究和神经科学理论提供灵感。深度学习已经利用了几种关键的归纳偏见，这项工作考虑了更大的清单，重点是关注高级和顺序有意识的处理的工作。阐明这些特定原则的目的是，它们有可能帮助我们建立从人类的能力中受益于灵活分布和系统概括的能力的AI系统，目前，这是一个领域艺术机器学习和人类智力。

背景信息：在过去几年中，机器学习（ML）一直是许多创新的核心。然而，包括在所谓的“安全关键”系统中，例如汽车或航空的系统已经被证明是非常具有挑战性的，因为ML的范式转变为ML带来完全改变传统认证方法。目的：本文旨在阐明与ML为基础的安全关键系统认证有关的挑战，以及文献中提出的解决方案，以解决它们，回答问题的问题如何证明基于机器学习的安全关键系统？'方法：我们开展2015年至2020年至2020年之间发布的研究论文的系统文献综述（SLR），涵盖了与ML系统认证有关的主题。总共确定了217篇论文涵盖了主题，被认为是ML认证的主要支柱：鲁棒性，不确定性，解释性，验证，安全强化学习和直接认证。我们分析了每个子场的主要趋势和问题，并提取了提取的论文的总结。结果：单反结果突出了社区对该主题的热情，以及在数据集和模型类型方面缺乏多样性。它还强调需要进一步发展学术界和行业之间的联系，以加深域名研究。最后，它还说明了必须在上面提到的主要支柱之间建立连接的必要性，这些主要柱主要主要研究。结论：我们强调了目前部署的努力，以实现ML基于ML的软件系统，并讨论了一些未来的研究方向。

我们为大脑和行为提供了一般的理论框架，这些框架是进化的和计算方式。我们抽象模型中的大脑是一个节点和边缘网络。虽然它与标准神经网络模型有一些相似之处，但随着我们所示，存在一些显着差异。我们网络中的节点和边缘都具有权重和激活级别。它们充当使用一组相对简单的规则来确定激活级别和权重的概率传感器，以通过输入，生成输出，并相互影响。我们表明这些简单的规则能够实现允许网络代表越来越复杂的知识的学习过程，并同时充当促进规划，决策和行为执行的计算设备。通过指定网络的先天（遗传）组件，我们展示了进化如何以初始的自适应规则和目标赋予网络，然后通过学习来丰富。我们展示了网络的开发结构（这决定了大脑可以做些什么以及如何良好）受影响数据输入分布的机制和确定学习参数的机制之间的共同进化协调的批判性影响（在程序中使用按节点和边缘运行）。最后，我们考虑了模型如何占了学习领域的各种调查结果，如何解决思想和行为的一些挑战性问题，例如与设定目标和自我控制相关的问题，以及它如何帮助理解一些认知障碍。

人工智能（AI）的价值分配问题询问我们如何确保人造系统的“价值”（即，客观函数）与人类的价值一致。在本文中，我认为语言交流（自然语言）是稳健价值对齐的必要条件。我讨论了这一主张的真相对试图确保AI系统价值一致的研究计划所带来的后果；或者，更谨慎地设计强大的有益或道德人造代理。

如果未来的AI系统在新的情况下是可靠的安全性，那么他们将需要纳入指导它们的一般原则，以便强烈地认识到哪些结果和行为将是有害的。这样的原则可能需要得到约束力的监管制度的支持，该法规需要广泛接受的基本原则。它们还应该足够具体用于技术实施。本文从法律中汲取灵感，解释了负面的人权如何履行此类原则的作用，并为国际监管制度以及为未来的AI系统建立技术安全限制的基础。

We are currently unable to specify human goals and societal values in a way that reliably directs AI behavior. Law-making and legal interpretation form a computational engine that converts opaque human values into legible directives. "Law Informs Code" is the research agenda capturing complex computational legal processes, and embedding them in AI. Similar to how parties to a legal contract cannot foresee every potential contingency of their future relationship, and legislators cannot predict all the circumstances under which their proposed bills will be applied, we cannot ex ante specify rules that provably direct good AI behavior. Legal theory and practice have developed arrays of tools to address these specification problems. For instance, legal standards allow humans to develop shared understandings and adapt them to novel situations. In contrast to more prosaic uses of the law (e.g., as a deterrent of bad behavior through the threat of sanction), leveraged as an expression of how humans communicate their goals, and what society values, Law Informs Code. We describe how data generated by legal processes (methods of law-making, statutory interpretation, contract drafting, applications of legal standards, legal reasoning, etc.) can facilitate the robust specification of inherently vague human goals. This increases human-AI alignment and the local usefulness of AI. Toward society-AI alignment, we present a framework for understanding law as the applied philosophy of multi-agent alignment. Although law is partly a reflection of historically contingent political power - and thus not a perfect aggregation of citizen preferences - if properly parsed, its distillation offers the most legitimate computational comprehension of societal values available. If law eventually informs powerful AI, engaging in the deliberative political process to improve law takes on even more meaning.

随着AI的进展继续前进，重要的是要知道高级系统将如何做出选择以及以什么方式失败。机器已经可以在某些领域中超越人类，并了解如何安全地构建可能在人类层面上具有或高于人类水平的能力的人特别关注。人们可能会怀疑，人为智能（AGI）和人为的超智能（ASI）系统应被建模为人类无法可靠地超越人类的东西。作为对这一假设的挑战，本文提出了阿喀琉斯高跟假说，该假设指出，即使是潜在的超级智能系统，也可能具有稳定的决策理论妄想，这会导致他们在对抗环境中做出明显的非理性决策。在对决策理论文献中相关困境和悖论的调查中，以此假设的背景讨论了许多潜在的致命弱点。为了理解这些弱点可能被植入系统的方式，做出了一些新颖的贡献。

在流行媒体中，人造代理商的意识出现与同时实现人类或超人水平智力的那些相同的代理之间通常存在联系。在这项工作中，我们探讨了意识和智力之间这种看似直观的联系的有效性和潜在应用。我们通过研究与三种当代意识功能理论相关的认知能力：全球工作空间理论（GWT），信息生成理论（IGT）和注意力模式理论（AST）。我们发现，这三种理论都将有意识的功能专门与人类领域将军智力的某些方面联系起来。有了这个见解，我们转向人工智能领域（AI），发现尽管远未证明一般智能，但许多最先进的深度学习方法已经开始纳入三个功能的关键方面理论。确定了这一趋势后，我们以人类心理时间旅行的激励例子来提出方式，其中三种理论中每种理论的见解都可以合并为一个单一的统一和可实施的模型。鉴于三种功能理论中的每一种都可以通过认知能力来实现这一可能，因此，具有精神时间旅行的人造代理不仅具有比当前方法更大的一般智力，而且还与我们当前对意识功能作用的理解更加一致在人类中，这使其成为AI研究的有希望的近期目标。

Curiosity for machine agents has been a focus of lively research activity. The study of human and animal curiosity, particularly specific curiosity, has unearthed several properties that would offer important benefits for machine learners, but that have not yet been well-explored in machine intelligence. In this work, we conduct a comprehensive, multidisciplinary survey of the field of animal and machine curiosity. As a principal contribution of this work, we use this survey as a foundation to introduce and define what we consider to be five of the most important properties of specific curiosity: 1) directedness towards inostensible referents, 2) cessation when satisfied, 3) voluntary exposure, 4) transience, and 5) coherent long-term learning. As a second main contribution of this work, we show how these properties may be implemented together in a proof-of-concept reinforcement learning agent: we demonstrate how the properties manifest in the behaviour of this agent in a simple non-episodic grid-world environment that includes curiosity-inducing locations and induced targets of curiosity. As we would hope, our example of a computational specific curiosity agent exhibits short-term directed behaviour while updating long-term preferences to adaptively seek out curiosity-inducing situations. This work, therefore, presents a landmark synthesis and translation of specific curiosity to the domain of machine learning and reinforcement learning and provides a novel view into how specific curiosity operates and in the future might be integrated into the behaviour of goal-seeking, decision-making computational agents in complex environments.

我们研究目标不当，这是强化学习（RL）中分布的概括失败。当RL代理商保留其功能过失但追求错误的目标时，就会发生目标失败失败。例如，代理商可能会继续有能力避免障碍，但要导航到错误的地方。相比之下，以前的工作通常集中在能力概括性失败上，因为代理在测试时间无法做任何明智的事情。我们将能力和目标泛化之间的这种区别形式化，提供了目标不当的第一个经验证明，并呈现了其原因的部分特征。

The increasing capabilities of artificial intelligence (AI) systems make it ever more important that we interpret their internals to ensure that their intentions are aligned with human values. Yet there is reason to believe that misaligned artificial intelligence will have a convergent instrumental incentive to make its thoughts difficult for us to interpret. In this article, I discuss many ways that a capable AI might circumvent scalable interpretability methods and suggest a framework for thinking about these potential future risks.

组合优化是运营研究和计算机科学领域的一个公认领域。直到最近，它的方法一直集中在孤立地解决问题实例，而忽略了它们通常源于实践中的相关数据分布。但是，近年来，人们对使用机器学习，尤其是图形神经网络（GNN）的兴趣激增，作为组合任务的关键构件，直接作为求解器或通过增强确切的求解器。GNN的电感偏差有效地编码了组合和关系输入，因为它们对排列和对输入稀疏性的意识的不变性。本文介绍了对这个新兴领域的最新主要进步的概念回顾，旨在优化和机器学习研究人员。

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.

即将开发我们呼叫所体现的系统的新一代越来越自主和自学习系统。在将这些系统部署到真实上下文中，我们面临各种工程挑战，因为它以有益的方式协调所体现的系统的行为至关重要，确保他们与我们以人为本的社会价值观的兼容性，并且设计可验证安全可靠的人类-Machine互动。我们正在争辩说，引发系统工程将来自嵌入到体现系统的温室，并确保动态联合的可信度，这种情况意识到的情境意识，意图，探索，探险，不断发展，主要是不可预测的，越来越自主的体现系统在不确定，复杂和不可预测的现实世界环境中。我们还识别了许多迫切性的系统挑战，包括可信赖的体现系统，包括强大而人为的AI，认知架构，不确定性量化，值得信赖的自融化以及持续的分析和保证。

The reinforcement learning paradigm is a popular way to address problems that have only limited environmental feedback, rather than correctly labeled examples, as is common in other machine learning contexts. While significant progress has been made to improve learning in a single task, the idea of transfer learning has only recently been applied to reinforcement learning tasks. The core idea of transfer is that experience gained in learning to perform one task can help improve learning performance in a related, but different, task. In this article we present a framework that classifies transfer learning methods in terms of their capabilities and goals, and then use it to survey the existing literature, as well as to suggest future directions for transfer learning work.

This paper surveys the eld of reinforcement learning from a computer-science perspective. It is written to be accessible to researchers familiar with machine learning. Both the historical basis of the eld and a broad selection of current work are summarized. Reinforcement learning is the problem faced by an agent that learns behavior through trial-and-error interactions with a dynamic environment. The work described here has a resemblance to work in psychology, but di ers considerably in the details and in the use of the word \reinforcement." The paper discusses central issues of reinforcement learning, including trading o exploration and exploitation, establishing the foundations of the eld via Markov decision theory, learning from delayed reinforcement, constructing empirical models to accelerate learning, making use of generalization and hierarchy, and coping with hidden state. It concludes with a survey of some implemented systems and an assessment of the practical utility of current methods for reinforcement learning.