We propose a new model-based offline RL framework, called Adversarial Models for Offline Reinforcement Learning (ARMOR), which can robustly learn policies to improve upon an arbitrary baseline policy regardless of data coverage. Based on the concept of relative pessimism, ARMOR is designed to optimize for the worst-case relative performance when facing uncertainty. In theory, we prove that the learned policy of ARMOR never degrades the performance of the baseline policy with any admissible hyperparameter, and can learn to compete with the best policy within data coverage when the hyperparameter is well tuned, and the baseline policy is supported by the data. Such a robust policy improvement property makes ARMOR especially suitable for building real-world learning systems, because in practice ensuring no performance degradation is imperative before considering any benefit learning can bring.
translated by 谷歌翻译
我们根据相对悲观主义的概念,在数据覆盖不足的情况下提出了经过对抗训练的演员评论家(ATAC),这是一种新的无模型算法(RL)。 ATAC被设计为两人Stackelberg游戏:政策演员与受对抗训练的价值评论家竞争,后者发现参与者不如数据收集行为策略的数据一致方案。我们证明,当演员在两人游戏中不后悔时,运行ATAC会产生一项政策,证明1)在控制悲观程度的各种超级参数上都超过了行为政策,而2)与最佳竞争。 policy covered by data with appropriately chosen hyperparameters.与现有作品相比,尤其是我们的框架提供了一般函数近似的理论保证,也提供了可扩展到复杂环境和大型数据集的深度RL实现。在D4RL基准测试中,ATAC在一系列连续的控制任务上始终优于最先进的离线RL算法。
translated by 谷歌翻译
使用悲观,推理缺乏详尽的勘探数据集时的脱机强化学习最近颇具知名度。尽管它增加了算法的鲁棒性,过于悲观的推理可以在排除利好政策的发现,这是流行的基于红利悲观的问题同样有害。在本文中,我们介绍一般函数近似的Bellman-一致悲观的概念:不是计算逐点下界的值的功能,我们在超过设定的与贝尔曼方程一致的功能的初始状态实现悲观。我们的理论保证只需要贝尔曼封闭性作为探索性的设置标准,其中基于奖金的情况下的悲观情绪未能提供担保。即使在线性函数逼近的特殊情况下更强的表现力假设成立,我们的结果由$ \ mathcal {}Ø(d)在其样品的复杂$在最近的基于奖金的方法改善的时候,动作的空间是有限的。值得注意的是,我们的算法,能够自动适应事后最好的偏差 - 方差折中,而大多数现有的方法中需要调整的额外超参数的先验。
translated by 谷歌翻译
离线增强学习(RL)可以从先前收集的数据中进行有效的学习,而无需探索,这在探索昂贵甚至不可行时在现实世界应用中显示出巨大的希望。折扣因子$ \ gamma $在提高在线RL样本效率和估计准确性方面起着至关重要的作用,但是折现因子在离线RL中的作用尚未得到很好的探索。本文研究了$ \ gamma $在离线RL中的两个明显影响,并通过理论分析,即正则化效果和悲观效应。一方面,$ \ gamma $是在现有离线技术下以样本效率而定的最佳选择的监管机构。另一方面,较低的指导$ \ gamma $也可以看作是一种悲观的方式,我们在最坏的模型中优化了政策的性能。我们通过表格MDP和标准D4RL任务从经验上验证上述理论观察。结果表明,折现因子在离线RL算法的性能中起着至关重要的作用,无论是在现有的离线方法的小型数据制度下还是在没有其他保守主义的大型数据制度中。
translated by 谷歌翻译
Offline reinforcement learning (RL) concerns pursuing an optimal policy for sequential decision-making from a pre-collected dataset, without further interaction with the environment. Recent theoretical progress has focused on developing sample-efficient offline RL algorithms with various relaxed assumptions on data coverage and function approximators, especially to handle the case with excessively large state-action spaces. Among them, the framework based on the linear-programming (LP) reformulation of Markov decision processes has shown promise: it enables sample-efficient offline RL with function approximation, under only partial data coverage and realizability assumptions on the function classes, with favorable computational tractability. In this work, we revisit the LP framework for offline RL, and advance the existing results in several aspects, relaxing certain assumptions and achieving optimal statistical rates in terms of sample size. Our key enabler is to introduce proper constraints in the reformulation, instead of using any regularization as in the literature, sometimes also with careful choices of the function classes and initial state distributions. We hope our insights further advocate the study of the LP framework, as well as the induced primal-dual minimax optimization, in offline RL.
translated by 谷歌翻译
Two central paradigms have emerged in the reinforcement learning (RL) community: online RL and offline RL. In the online RL setting, the agent has no prior knowledge of the environment, and must interact with it in order to find an $\epsilon$-optimal policy. In the offline RL setting, the learner instead has access to a fixed dataset to learn from, but is unable to otherwise interact with the environment, and must obtain the best policy it can from this offline data. Practical scenarios often motivate an intermediate setting: if we have some set of offline data and, in addition, may also interact with the environment, how can we best use the offline data to minimize the number of online interactions necessary to learn an $\epsilon$-optimal policy? In this work, we consider this setting, which we call the \textsf{FineTuneRL} setting, for MDPs with linear structure. We characterize the necessary number of online samples needed in this setting given access to some offline dataset, and develop an algorithm, \textsc{FTPedel}, which is provably optimal. We show through an explicit example that combining offline data with online interactions can lead to a provable improvement over either purely offline or purely online RL. Finally, our results illustrate the distinction between \emph{verifiable} learning, the typical setting considered in online RL, and \emph{unverifiable} learning, the setting often considered in offline RL, and show that there is a formal separation between these regimes.
translated by 谷歌翻译
离线增强学习(RL)的样本效率保证通常依赖于对功能类别(例如Bellman-Completeness)和数据覆盖范围(例如,全政策浓缩性)的强有力的假设。尽管最近在放松这些假设方面做出了努力,但现有作品只能放松这两个因素之一,从而使另一个因素的强烈假设完好无损。作为一个重要的开放问题,我们是否可以实现对这两个因素的假设较弱的样本效率离线RL?在本文中,我们以积极的态度回答了这个问题。我们基于MDP的原始偶对偶进行分析了一种简单的算法,其中双重变量(打折占用)是使用密度比函数对离线数据进行建模的。通过适当的正则化,我们表明该算法仅在可变性和单极浓缩性下具有多项式样品的复杂性。我们还基于不同的假设提供了替代分析,以阐明离线RL原始二算法的性质。
translated by 谷歌翻译
我们考虑在离线增强学习中有一个具有挑战性的理论问题(RL):仅在功能近似器的可靠性型假设下,通过缺乏足够覆盖的数据集获得样本效率保证。尽管现有的理论已经在可实现性和非探索数据下分别解决了学习,但没有工作能够同时解决这两者(除了我们对详细比较的并发工作除外)。在额外的差距假设下,我们根据边缘化重要性采样(MIS)形成的版本空间(MIS)为简单的悲观算法提供保证,并且保证只需要数据来涵盖最佳策略和功能类,以实现最佳价值和最佳价值和密度比函数。尽管在RL理论的其他领域中使用了类似的差距假设,但我们的工作是第一个识别离线RL中差距假设的实用性和新型机制,其功能近似较弱。
translated by 谷歌翻译
我们在面对未衡量的混杂因素时研究离线增强学习(RL)。由于缺乏与环境的在线互动,离线RL面临以下两个重大挑战:(i)代理可能会被未观察到的状态变量混淆; (ii)提前收集的离线数据不能为环境提供足够的覆盖范围。为了应对上述挑战,我们借助工具变量研究了混杂的MDP中的政策学习。具体而言,我们首先建立了基于和边缘化的重要性采样(MIS)的识别结果,以确定混杂的MDP中的预期总奖励结果。然后,通过利用悲观主义和我们的认同结果,我们提出了各种政策学习方法,并具有有限样本的次级临时性保证,可以在最小的数据覆盖范围和建模假设下找到最佳的课堂政策。最后,我们广泛的理论研究和一项由肾脏移植动机的数值研究证明了该方法的有希望的表现。
translated by 谷歌翻译
We study sample efficient reinforcement learning (RL) under the general framework of interactive decision making, which includes Markov decision process (MDP), partially observable Markov decision process (POMDP), and predictive state representation (PSR) as special cases. Toward finding the minimum assumption that empowers sample efficient learning, we propose a novel complexity measure, generalized eluder coefficient (GEC), which characterizes the fundamental tradeoff between exploration and exploitation in online interactive decision making. In specific, GEC captures the hardness of exploration by comparing the error of predicting the performance of the updated policy with the in-sample training error evaluated on the historical data. We show that RL problems with low GEC form a remarkably rich class, which subsumes low Bellman eluder dimension problems, bilinear class, low witness rank problems, PO-bilinear class, and generalized regular PSR, where generalized regular PSR, a new tractable PSR class identified by us, includes nearly all known tractable POMDPs. Furthermore, in terms of algorithm design, we propose a generic posterior sampling algorithm, which can be implemented in both model-free and model-based fashion, under both fully observable and partially observable settings. The proposed algorithm modifies the standard posterior sampling algorithm in two aspects: (i) we use an optimistic prior distribution that biases towards hypotheses with higher values and (ii) a loglikelihood function is set to be the empirical loss evaluated on the historical data, where the choice of loss function supports both model-free and model-based learning. We prove that the proposed algorithm is sample efficient by establishing a sublinear regret upper bound in terms of GEC. In summary, we provide a new and unified understanding of both fully observable and partially observable RL.
translated by 谷歌翻译
在阻碍强化学习(RL)到现实世界中的问题的原因之一,两个因素至关重要:与培训相比,数据有限和测试环境的不匹配。在本文中,我们试图通过分配强大的离线RL的问题同时解决这些问题。特别是,我们学习了一个从源环境中获得的历史数据,并优化了RL代理,并在扰动的环境中表现良好。此外,我们考虑将算法应用于大规模问题的线性函数近似。我们证明我们的算法可以实现$ O(1/\ sqrt {k})$的次级临时性,具体取决于线性函数尺寸$ d $,这似乎是在此设置中使用样品复杂性保证的第一个结果。进行了不同的实验以证明我们的理论发现,显示了我们算法与非持bust算法的优越性。
translated by 谷歌翻译
本文涉及离线增强学习(RL)中模型鲁棒性和样本效率的核心问题,该问题旨在学习从没有主动探索的情况下从历史数据中执行决策。由于环境的不确定性和变异性,至关重要的是,学习强大的策略(尽可能少的样本),即使部署的环境偏离用于收集历史记录数据集的名义环境时,该策略也能很好地执行。我们考虑了离线RL的分布稳健公式,重点是标签非平稳的有限摩托稳健的马尔可夫决策过程,其不确定性设置为Kullback-Leibler Divergence。为了与样本稀缺作用,提出了一种基于模型的算法,该算法将分布强劲的价值迭代与面对不确定性时的悲观原理结合在一起,通过对稳健的价值估计值进行惩罚,以精心设计的数据驱动的惩罚项进行惩罚。在对历史数据集的轻度和量身定制的假设下,该数据集测量分布变化而不需要完全覆盖州行动空间,我们建立了所提出算法的有限样本复杂性,进一步表明,鉴于几乎无法改善的情况,匹配信息理论下限至地平线长度的多项式因素。据我们所知,这提供了第一个在模型不确定性和部分覆盖范围内学习的近乎最佳的稳健离线RL算法。
translated by 谷歌翻译
This paper studies offline policy learning, which aims at utilizing observations collected a priori (from either fixed or adaptively evolving behavior policies) to learn an optimal individualized decision rule that achieves the best overall outcomes for a given population. Existing policy learning methods rely on a uniform overlap assumption, i.e., the propensities of exploring all actions for all individual characteristics are lower bounded in the offline dataset; put differently, the performance of the existing methods depends on the worst-case propensity in the offline dataset. As one has no control over the data collection process, this assumption can be unrealistic in many situations, especially when the behavior policies are allowed to evolve over time with diminishing propensities for certain actions. In this paper, we propose a new algorithm that optimizes lower confidence bounds (LCBs) -- instead of point estimates -- of the policy values. The LCBs are constructed using knowledge of the behavior policies for collecting the offline data. Without assuming any uniform overlap condition, we establish a data-dependent upper bound for the suboptimality of our algorithm, which only depends on (i) the overlap for the optimal policy, and (ii) the complexity of the policy class we optimize over. As an implication, for adaptively collected data, we ensure efficient policy learning as long as the propensities for optimal actions are lower bounded over time, while those for suboptimal ones are allowed to diminish arbitrarily fast. In our theoretical analysis, we develop a new self-normalized type concentration inequality for inverse-propensity-weighting estimators, generalizing the well-known empirical Bernstein's inequality to unbounded and non-i.i.d. data.
translated by 谷歌翻译
我们研究了在偏见的可观察性模型下,在对抗性匪徒问题中的在线学习问题,称为政策反馈。在这个顺序决策问题中,学习者无法直接观察其奖励,而是看到由另一个未知策略并行运行的奖励(行为策略)。学习者必须在这种情况下面临另一个挑战:由于他们的控制之外的观察结果有限,学习者可能无法同样估算每个政策的价值。为了解决这个问题,我们提出了一系列算法,以保证任何比较者政策与行为政策之间的自然不匹配概念的范围,从而提高了对观察结果良好覆盖的比较者的绩效。我们还为对抗性线性上下文匪徒的设置提供了扩展,并通过一组实验验证理论保证。我们的关键算法想法是调整最近在非政策强化学习背景下流行的悲观奖励估计量的概念。
translated by 谷歌翻译
我们研究了批量策略优化中模型选择的问题:给定固定的部分反馈数据集和$ M $ Model类,学习具有与最佳模型类的策略具有竞争力的性能的策略。通过识别任何模型选择算法应最佳地折衷的错误,以线性模型类在与线性模型类中的内容匪徒设置中的问题正式化。(1)近似误差,(2)统计复杂性,(3 )覆盖范围。前两个来源是在监督学习的模型选择中常见的,在最佳的交易中,这些属性得到了很好的研究。相比之下,第三个源是批量策略优化的唯一,并且是由于设置所固有的数据集移位。首先表明,没有批处理策略优化算法可以同时实现所有三个的保证,展示批量策略优化的困难之间的显着对比,以及监督学习中的积极结果。尽管存在这种负面结果,但我们表明,在三个错误源中的任何一个都可以实现实现剩下的两个近乎oracle不平等的算法。我们通过实验结论,证明了这些算法的功效。
translated by 谷歌翻译
本文介绍了一项有关离线增强学习中依赖间隙依赖样品复杂性的系统研究。先前的工作显示了何时最佳策略和行为策略之间的密度比上限(最佳策略覆盖范围假设),则代理可以实现$ o \ left(\ frac {1} {\ epsilon^2} \ right)$ rate,这也是最小值的最佳。我们在最佳策略覆盖范围假设下显示,当在最佳$ q $ unction中存在积极的子临时差距时,可以将费率提高到$ o \ left(\ frac {1} {\ epsilon} \ right)$。。此外,我们显示了行为策略的访问概率何时在最佳策略的访问概率为正(统一的最佳策略覆盖范围假设)的状态下,均匀下降,识别最佳政策的样本复杂性独立于$ \ frac {1} {\ epsilon} $。最后,我们呈现几乎匹配的下限,以补充我们的间隙依赖性上限。
translated by 谷歌翻译
本文介绍了一种简单的有效学习算法,用于一般顺序决策。该算法将探索的乐观与模型估计的最大似然估计相结合,因此被命名为OMLE。我们证明,Omle了解了多项式数量的样本中一系列非常丰富的顺序决策问题的近乎最佳策略。这个丰富的类别不仅包括大多数已知的基于模型的基于模型的强化学习(RL)问题(例如表格MDP,计算的MDP,低证人等级问题,表格弱弱/可观察到的POMDP和多步可解码的POMDP),但是同样,许多新的具有挑战性的RL问题,尤其是在可观察到的部分环境中,这些问题以前尚不清楚。值得注意的是,本文解决的新问题包括(1)具有连续观察和功能近似的可观察到的POMDP,在其中我们实现了完全独立于观察空间的第一个样品复杂性; (2)条件良好的低级顺序决策问题(也称为预测状态表示(PSRS)),其中包括并概括了所有已知的可牵引的POMDP示例,这些示例在更固有的表示下; (3)在帆条件下进行一般顺序决策问题,这统一了我们在完全可观察和部分可观察的设置中对基于模型的RL的现有理解。帆条件是由本文确定的,可以将其视为贝尔曼/证人等级的自然概括,以解决部分可观察性。
translated by 谷歌翻译
本文为表格马尔可夫决策过程(MDP)提供了第一种多项式时间算法,该算法享受了遗憾的界限\ emph {独立于计划范围}。具体来说,我们考虑具有$ S $州的表格MDP,$ A $ ACTICY,计划范围$ h $,总奖励为$ 1 $,代理商播放$ K $ evipodes。我们设计了一种实现$ o \ left(\ mathrm {poly}(s,a,a,\ log k)\ sqrt {k} \ right)$遗憾的算法(\ mathrm {poly}(s,a,a,\ log k)polylog}(h)$依赖项〜\ citep {zhang2020 reininforcement}或对$ s $〜\ citep {li2021settling}具有指数依赖关系。我们的结果依赖于一系列新的结构引理,从而建立了固定策略的近似能力,稳定性和浓度特性,这些策略可以在与马尔可夫链有关的其他问题中应用。
translated by 谷歌翻译
我们研究马尔可夫决策过程(MDP)框架中的离线数据驱动的顺序决策问题。为了提高学习政策的概括性和适应性,我们建议通过一套关于在政策诱导的固定分配所在的分发的一套平均奖励来评估每项政策。给定由某些行为策略生成的多个轨迹的预收集数据集,我们的目标是在预先指定的策略类中学习一个强大的策略,可以最大化此集的最小值。利用半参数统计的理论,我们开发了一种统计上有效的策略学习方法,用于估算DE NED强大的最佳政策。在数据集中的总决策点方面建立了达到对数因子的速率最佳遗憾。
translated by 谷歌翻译
We study episodic two-player zero-sum Markov games (MGs) in the offline setting, where the goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset collected a priori. When the dataset does not have uniform coverage over all policy pairs, finding an approximate NE involves challenges in three aspects: (i) distributional shift between the behavior policy and the optimal policy, (ii) function approximation to handle large state space, and (iii) minimax optimization for equilibrium solving. We propose a pessimism-based algorithm, dubbed as pessimistic minimax value iteration (PMVI), which overcomes the distributional shift by constructing pessimistic estimates of the value functions for both players and outputs a policy pair by solving NEs based on the two value functions. Furthermore, we establish a data-dependent upper bound on the suboptimality which recovers a sublinear rate without the assumption on uniform coverage of the dataset. We also prove an information-theoretical lower bound, which suggests that the data-dependent term in the upper bound is intrinsic. Our theoretical results also highlight a notion of "relative uncertainty", which characterizes the necessary and sufficient condition for achieving sample efficiency in offline MGs. To the best of our knowledge, we provide the first nearly minimax optimal result for offline MGs with function approximation.
translated by 谷歌翻译