离线政策优化可能会对许多现实世界的决策问题产生重大影响,因为在线学习在许多应用中可能是不可行的。重要性采样及其变体是离线策略评估中一种常用的估计器类型,此类估计器通常不需要关于价值函数或决策过程模型功能类的属性和代表性能力的假设。在本文中,我们确定了一种重要的过度拟合现象,以优化重要性加权收益,在这种情况下,学到的政策可以基本上避免在最初的状态空间的一部分中做出一致的决策。我们提出了一种算法,以避免通过新的每个国家 - 邻居标准化约束过度拟合,并提供对拟议算法的理论理由。我们还显示了以前尝试这种方法的局限性。我们在以医疗风格的模拟器为中测试算法,该模拟器是从真实医院收集的记录数据集和连续的控制任务。这些实验表明,与最先进的批处理学习算法相比,所提出的方法的过度拟合和更好的测试性能。
translated by 谷歌翻译
Counterfactual reasoning from logged data has become increasingly important for many applications such as web advertising or healthcare. In this paper, we address the problem of learning stochastic policies with continuous actions from the viewpoint of counterfactual risk minimization (CRM). While the CRM framework is appealing and well studied for discrete actions, the continuous action case raises new challenges about modelization, optimization, and~offline model selection with real data which turns out to be particularly challenging. Our paper contributes to these three aspects of the CRM estimation pipeline. First, we introduce a modelling strategy based on a joint kernel embedding of contexts and actions, which overcomes the shortcomings of previous discretization approaches. Second, we empirically show that the optimization aspect of counterfactual learning is important, and we demonstrate the benefits of proximal point algorithms and differentiable estimators. Finally, we propose an evaluation protocol for offline policies in real-world logged systems, which is challenging since policies cannot be replayed on test data, and we release a new large-scale dataset along with multiple synthetic, yet realistic, evaluation setups.
translated by 谷歌翻译
政策梯度(PG)算法是备受期待的强化学习对现实世界控制任务(例如机器人技术)的最佳候选人之一。但是,每当必须在物理系统上执行学习过程本身或涉及任何形式的人类计算机相互作用时,这些方法的反复试验性质就会提出安全问题。在本文中,我们解决了一种特定的安全公式,其中目标和危险都以标量奖励信号进行编码,并且学习代理被限制为从不恶化其性能,以衡量为预期的奖励总和。通过从随机优化的角度研究仅行为者的政策梯度,我们为广泛的参数政策建立了改进保证,从而将现有结果推广到高斯政策上。这与策略梯度估计器的差异的新型上限一起,使我们能够识别出具有很高概率的单调改进的元参数计划。两个关键的元参数是参数更新的步长和梯度估计的批处理大小。通过对这些元参数的联合自适应选择,我们获得了具有单调改进保证的政策梯度算法。
translated by 谷歌翻译
Reinforcement learning (RL) is one of the most vibrant research frontiers in machine learning and has been recently applied to solve a number of challenging problems. In this paper, we primarily focus on off-policy evaluation (OPE), one of the most fundamental topics in RL. In recent years, a number of OPE methods have been developed in the statistics and computer science literature. We provide a discussion on the efficiency bound of OPE, some of the existing state-of-the-art OPE methods, their statistical properties and some other related research directions that are currently actively explored.
translated by 谷歌翻译
在线强化学习(RL)算法通常难以在复杂的人体面对应用中部署,因为它们可能会缓慢学习并且早期性能差。为了解决这个问题,我们介绍了一种结合人类洞察速度学习的实用算法。我们的算法,约束采样增强学习(CSRL)将现有域知识包含为RL策略的约束/限制。它需要多种潜在的政策限制,以保持稳健性,以便在利用有用的时击败个体限制,以便快速学习。鉴于基础RL学习算法(例如UCRL,DQN,Rainbow),我们提出了对消除方案的上下置信度,该方案利用了限制与其观察性能之间的关系,以便自适应地切换它们。我们将我们的算法用DQN型算法和UCRL作为基础算法,并在四种环境中评估我们的算法,包括基于实际数据的三个模拟器:建议,教育活动排序和HIV处理测序。在所有情况下,CSRL比基线更快地学习良好的政策。
translated by 谷歌翻译
依赖于太多的实验来学习良好的行动,目前的强化学习(RL)算法在现实世界的环境中具有有限的适用性,这可能太昂贵,无法探索探索。我们提出了一种批量RL算法,其中仅使用固定的脱机数据集来学习有效策略,而不是与环境的在线交互。批量RL中的有限数据产生了在培训数据中不充分表示的状态/行动的价值估计中的固有不确定性。当我们的候选政策从生成数据的候选政策发散时,这导致特别严重的外推。我们建议通过两个直接的惩罚来减轻这个问题:减少这种分歧的政策限制和减少过于乐观估计的价值约束。在全面的32个连续动作批量RL基准测试中,我们的方法对最先进的方法进行了比较,无论如何收集离线数据如何。
translated by 谷歌翻译
脱机强化学习 - 从一批数据中学习策略 - 是难以努力的:如果没有制造强烈的假设,它很容易构建实体算法失败的校长。在这项工作中,我们考虑了某些现实世界问题的财产,其中离线强化学习应该有效:行动仅对一部分产生有限的行动。我们正规化并介绍此动作影响规律(AIR)财产。我们进一步提出了一种算法,该算法假定和利用AIR属性,并在MDP满足空气时绑定输出策略的子优相。最后,我们展示了我们的算法在定期保留的两个模拟环境中跨越不同的数据收集策略占据了现有的离线强度学习算法。
translated by 谷歌翻译
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.
translated by 谷歌翻译
大多数前往离线强化学习(RL)的方法都采取了一种迭代演员 - 批评批评,涉及违规评估。在本文中,我们展示了使用行为政策的政策Q估计来令人惊讶地执行一步的Q估计,从而简单地执行一个受限制/正规化的政策改进的步骤。该一步算法在大部分D4RL基准测试中击败了先前报告的迭代算法的结果。一步基线实现了这种强劲的性能,同时对超公数更简单,更强大而不是先前提出的迭代算法。我们认为迭代方法的表现相对较差是在违反政策评估中固有的高方差,并通过对这些估计的重复优化的政策进行放大。此外,我们假设一步算法的强大性能是由于环境和行为政策中有利结构的组合。
translated by 谷歌翻译
Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected, static datasets without further interaction. However, in practice, offline RL presents a major challenge, and standard off-policy RL methods can fail due to overestimation of values induced by the distributional shift between the dataset and the learned policy, especially when training on complex and multi-modal data distributions. In this paper, we propose conservative Q-learning (CQL), which aims to address these limitations by learning a conservative Q-function such that the expected value of a policy under this Q-function lower-bounds its true value. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a policy learning procedure with theoretical improvement guarantees. In practice, CQL augments the standard Bellman error objective with a simple Q-value regularizer which is straightforward to implement on top of existing deep Q-learning and actor-critic implementations. On both discrete and continuous control domains, we show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return, especially when learning from complex and multi-modal data distributions.Preprint. Under review.
translated by 谷歌翻译
Offline reinforcement learning (RL) refers to the problem of learning policies entirely from a large batch of previously collected data. This problem setting offers the promise of utilizing such datasets to acquire policies without any costly or dangerous active exploration. However, it is also challenging, due to the distributional shift between the offline training data and those states visited by the learned policy. Despite significant recent progress, the most successful prior methods are model-free and constrain the policy to the support of data, precluding generalization to unseen states. In this paper, we first observe that an existing model-based RL algorithm already produces significant gains in the offline setting compared to model-free approaches. However, standard model-based RL methods, designed for the online setting, do not provide an explicit mechanism to avoid the offline setting's distributional shift issue. Instead, we propose to modify the existing model-based RL methods by applying them with rewards artificially penalized by the uncertainty of the dynamics. We theoretically show that the algorithm maximizes a lower bound of the policy's return under the true MDP. We also characterize the trade-off between the gain and risk of leaving the support of the batch data. Our algorithm, Model-based Offline Policy Optimization (MOPO), outperforms standard model-based RL algorithms and prior state-of-the-art model-free offline RL algorithms on existing offline RL benchmarks and two challenging continuous control tasks that require generalizing from data collected for a different task. * equal contribution. † equal advising. Orders randomized.34th Conference on Neural Information Processing Systems (NeurIPS 2020),
translated by 谷歌翻译
非政策评估(OPE)方法是评估高风险领域(例如医疗保健)中的政策的关键工具,在这些领域,直接部署通常是不可行的,不道德的或昂贵的。当期望部署环境发生变化(即数据集偏移)时,对于OPE方法,在此类更改中对策略进行强大的评估非常重要。现有的方法考虑对可以任意改变环境的任何可观察到的任何可观察到的属性的大量转变。这通常会导致对公用事业的高度悲观估计,从而使可能对部署有用的政策无效。在这项工作中,我们通过研究领域知识如何帮助提供对政策公用事业的更现实的估计来解决上述问题。我们利用人类的投入,在环境的哪些方面可能会发生变化,并适应OPE方法仅考虑这些方面的转变。具体而言,我们提出了一个新颖的框架,可靠的OPE(绳索),该框架认为基于用户输入的数据中的协变量子集,并估算了这些变化下最坏情况的效用。然后,我们为OPE开发了对OPE的计算有效算法,这些算法对上述强盗和马尔可夫决策过程的上述变化很强。我们还理论上分析了这些算法的样品复杂性。从医疗领域进行的合成和现实世界数据集进行了广泛的实验表明,我们的方法不仅可以捕获现实的数据集准确地转移,而且还会导致较少的悲观政策评估。
translated by 谷歌翻译
我们考虑在离线域中的强化学习(RL)方法,没有其他在线数据收集,例如移动健康应用程序。计算机科学文献中的大多数现有策略优化算法都是在易于收集或模拟的在线设置中开发的。通过预采用的离线数据集,它们对移动健康应用程序的概括尚不清楚。本文的目的是开发一个新颖的优势学习框架,以便有效地使用预采用的数据进行策略优化。所提出的方法采用由任何现有的最新RL算法计算的最佳Q-估计器作为输入,并输出一项新策略,其价值比基于初始Q-得出的策略更快地收敛速度。估计器。进行广泛的数值实验以支持我们的理论发现。我们提出的方法的Python实现可在https://github.com/leyuanheart/seal上获得。
translated by 谷歌翻译
机器学习已成功构建许多顺序决策,作为监督预测,或通过加强学习的最佳决策政策识别。在数据约束的离线设置中,两种方法可能会失败,因为它们假设完全最佳行为或依赖于探索可能不存在的替代方案。我们介绍了一种固有的不同方法,该方法识别出状态空间的可能的“死角”。我们专注于重症监护病房中患者的状况,其中``“医疗死亡端”表明患者将过期,无论所有潜在的未来治疗序列如何。我们假设“治疗安全”为避免与其导致死亡事件的机会成比例的概率成比例的治疗,呈现正式证明,以及作为RL问题的帧发现。然后,我们将三个独立的深度神经模型进行自动化状态建设,死端发现和确认。我们的经验结果发现,死亡末端存在于脓毒症患者的真正临床数据中,并进一步揭示了安全处理与施用的差距。
translated by 谷歌翻译
本文关注的是,基于无限视野设置中预采用的观察数据,为目标策略的价值离线构建置信区间。大多数现有作品都假定不存在混淆观察到的动作的未测量变量。但是,在医疗保健和技术行业等实际应用中,这种假设可能会违反。在本文中,我们表明,使用一些辅助变量介导动作对系统动态的影响,目标策略的价值在混杂的马尔可夫决策过程中可以识别。基于此结果,我们开发了一个有效的非政策值估计器,该估计值可用于潜在模型错误指定并提供严格的不确定性定量。我们的方法是通过理论结果,从乘车共享公司获得的模拟和真实数据集证明的。python实施了建议的过程,请访问https://github.com/mamba413/cope。
translated by 谷歌翻译
在上下文土匪中,非政策评估(OPE)已在现实世界中迅速采用,因为它仅使用历史日志数据就可以离线评估新政策。不幸的是,当动作数量较大时,现有的OPE估计器(其中大多数是基于反相反的得分加权)会严重降解,并且可能会遭受极端偏见和差异。这挫败了从推荐系统到语言模型的许多应用程序中使用OPE。为了克服这个问题,我们提出了一个新的OPE估计器,即当动作嵌入在动作空间中提供结构时,利用边缘化的重要性权重。我们表征了所提出的估计器的偏差,方差和平方平方误差,并分析了动作嵌入提供了比常规估计器提供统计益处的条件。除了理论分析外,我们还发现,即使由于大量作用,现有估计量崩溃,经验性绩效的改善也可以实现可靠的OPE。
translated by 谷歌翻译
面对顺序决策问题时,能够预测如果使用新策略进行决策会发生什么会发生什么。这些预测通常必须基于在一些先前使用的决策规则下收集的数据。许多以前的方法使得这种违规(或反事实)估计的性能测量值的预期值称为返回。在本文中,我们采取了迈向普遍违规估算机(UNO)的第一步 - 为返回分配的任何参数提供截止政策估计和高信任界限。我们使用UNO来估计和同时限制均值,方差,量级/中位数,分位式范围,CVAR和返回的整个累积分布。最后,我们还在各种环境中讨论了UNO的适用性,包括完全可观察,部分可观察的(即,与未观察到的混乱),马尔可夫,非马尔可瓦尔,静止,平稳的非稳定性和离散分布转移。
translated by 谷歌翻译
顺序决策的违规政策评估方法可用于帮助识别拟议的决策政策优于当前基线政策。但是,新的决策政策可能比某些人的基线政策更好,但不是其他人。这有动力推动个性化和准确的单态治疗效果估算(HTES)。鉴于许多重要应用中存在的有限数据,个体预测可以以准确性和在这种预测中的准确性和置信度的成本。通过识别子组,我们开发一种平衡对个人化的需求,以通过识别相对于基线的新决策政策中的预期差异来自信地估计预期估计。我们提出了一种新的损失函数,用于在子组分区阶段期间的不确定性。在实验中,我们表明我们的方法可用于形成其他方法斗争的HTES的准确预测。
translated by 谷歌翻译
强化学习的最新出现为使用这些算法计算的参数估计值创造了强大的统计推断方法的需求。现有的在线学习中统计推断的方法仅限于涉及独立采样观察的设置,而现有的强化学习中统计推断方法(RL)仅限于批处理设置。在线引导程序是一种灵活,有效的方法,用于线性随机近似算法中的统计推断,但在涉及Markov噪声(例如RL)的设置中,其功效尚未探索。在本文中,我们研究了在线引导方法在RL中的统计推断的使用。特别是,我们专注于时间差异(TD)学习和梯度TD(GTD)学习算法,它们本身就是马尔可夫噪声下线性随机近似的特殊实例。该方法在策略评估中的统计推断上表明该方法在分布上是一致的,并且包括数值实验,以证明该算法在跨一系列实际RL环境中在统计推断任务上的有效性。
translated by 谷歌翻译
In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important for applications where the deployment of a bad policy can be dangerous or costly. We show empirically that our algorithm produces estimates that often have orders of magnitude lower mean squared error than existing methods-it makes more efficient use of the available data. Our new estimator is based on two advances: an extension of the doubly robust estimator (Jiang & Li, 2015), and a new way to mix between model based estimates and importance sampling based estimates.
translated by 谷歌翻译