一般强化学习领域(GRL)制定了从地下序贯决策的问题。互动史构成了系统的“地面”状态,其永远不会重复。一方面,该一般性允许GRL几乎可以模拟每个域,例如,\盗版,MDP,POMDPS,PSR和基于历史的环境。另一方面,一般而言,GRL的近乎最佳政策是完整历史的函数,这不仅会妨碍学习,也是在GRL中规划。对于规划部分的常用方式是代理商被赋予底层过程的马尔科维亚抽象。因此,它可以使用任何MDP计划算法查找近最佳策略。极端状态聚合(ESA)框架已将此想法扩展到非Markovian抽象,而不会影响通过(代理)MDP规划的可能性。 ESA的一个显着特征是它证明了$ o \ left的上限(\ varepsilon ^ { - a} \ cdot(1- \ gamma)^ { - 2a} \右)美元上的状态代理MDP(其中$ a $的是行动的数量,$ \ gamma $是折扣系数,$ \ varepsilon $是最优性的空白),其包含\ emph {supplyly} for \ emph {all}域。虽然普遍约束的可能性是非常显着的,但我们表明这一界限非常松散。我们提出了一种新的非MDP抽象,它允许$ o \ left的更好的上限(\ varepsilon ^ {-1} \ cdot(1- \ gamma)^ { - 2} \ cdot a \ cdot 2 ^ { } \右)$。此外,我们表明,通过使用一种动作顺序化方法。
translated by 谷歌翻译
许多基于模型的强化学习方法(MBRL)为他们可以提供的马尔可夫决策过程(MDP)模型的准确性和学习效率提供了保证。同时,状态抽象技术允许减少MDP的大小,同时相对于原始问题保持有限的损失。因此,令人惊讶的是,在结合两种技术时,即MBRL仅观察抽象状态时,没有任何保证可用。我们的理论分析表明,抽象可以在网上收集的样本(例如在现实世界中)引入依赖性,这意味着MBRL的大多数结果不能直接扩展到此设置。这项工作的新结果表明,可以使用Martingales的浓度不平等来克服此问题,并允许将R-MAX等算法的结果扩展到以抽象为设置的算法。因此,通过抽象的模型为抽象的RL生成了第一个性能保证:基于模型的强化学习。
translated by 谷歌翻译
This paper studies systematic exploration for reinforcement learning with rich observations and function approximation. We introduce a new model called contextual decision processes, that unifies and generalizes most prior settings. Our first contribution is a complexity measure, the Bellman rank , that we show enables tractable learning of near-optimal behavior in these processes and is naturally small for many well-studied reinforcement learning settings. Our second contribution is a new reinforcement learning algorithm that engages in systematic exploration to learn contextual decision processes with low Bellman rank. Our algorithm provably learns near-optimal behavior with a number of samples that is polynomial in all relevant parameters but independent of the number of unique observations. The approach uses Bellman error minimization with optimistic exploration and provides new insights into efficient exploration for reinforcement learning with function approximation.
translated by 谷歌翻译
大部分强化学习理论都建立在计算上难以实施的甲板上。专门用于在部分可观察到的马尔可夫决策过程(POMDP)中学习近乎最佳的政策,现有算法要么需要对模型动态(例如确定性过渡)做出强有力的假设,要么假设访问甲骨文作为解决艰难的计划或估算问题的访问子例程。在这项工作中,我们在合理的假设下开发了第一个用于POMDP的无Oracle学习算法。具体而言,我们给出了一种用于在“可观察” pomdps中学习的准化性时间端到端算法,其中可观察性是一个假设,即对国家而言,分离良好的分布诱导了分离良好的分布分布而不是观察。我们的技术规定了在不确定性下使用乐观原则来促进探索的更传统的方法,而是在构建策略涵盖的情况下提供了一种新颖的barycentric跨度应用。
translated by 谷歌翻译
Value-function approximation methods that operate in batch mode have foundational importance to reinforcement learning (RL). Finite sample guarantees for these methods often crucially rely on two types of assumptions: (1) mild distribution shift, and (2) representation conditions that are stronger than realizability. However, the necessity ("why do we need them?") and the naturalness ("when do they hold?") of such assumptions have largely eluded the literature. In this paper, we revisit these assumptions and provide theoretical results towards answering the above questions, and make steps towards a deeper understanding of value-function approximation.
translated by 谷歌翻译
我们在Isabelle定理箴言中展示了有限马尔可夫决定流程的正式化。我们专注于动态编程和使用加固学习代理所需的基础。特别是,我们从第一个原则(在标量和向量形式中)导出Bellman方程,导出产生任何策略P的预期值的向量计算,并继续证明存在一个普遍的最佳政策的存在折扣因子不到一个。最后,我们证明了价值迭代和策略迭代算法在有限的时间内工作,分别产生ePsilon - 最佳和完全最佳的政策。
translated by 谷歌翻译
我们研究了基于模型的无奖励加强学习,具有ePiSodic Markov决策过程的线性函数近似(MDP)。在此设置中,代理在两个阶段工作。在勘探阶段,代理商与环境相互作用并在没有奖励的情况下收集样品。在规划阶段,代理商给出了特定的奖励功能,并使用从勘探阶段收集的样品来学习良好的政策。我们提出了一种新的可直接有效的算法,称为UCRL-RFE在线性混合MDP假设,其中MDP的转换概率内核可以通过线性函数参数化,在状态,动作和下一个状态的三联体上定义的某些特征映射上参数化。我们展示了获得$ \ epsilon $-Optimal策略进行任意奖励函数,Ucrl-RFE需要以大多数$ \ tilde {\ mathcal {o}}来进行采样(h ^ 5d ^ 2 \ epsilon ^ { - 2})勘探阶段期间的$派对。在这里,$ H $是集的长度,$ d $是特征映射的尺寸。我们还使用Bernstein型奖金提出了一种UCRL-RFE的变种,并表明它需要在大多数$ \ TINDE {\ MATHCAL {o}}(H ^ 4D(H + D)\ epsilon ^ { - 2})进行样本$达到$ \ epsilon $ -optimal政策。通过构建特殊类的线性混合MDPS,我们还证明了对于任何无奖励算法,它需要至少为$ \ TINDE \ OMEGA(H ^ 2d \ epsilon ^ { - 2})$剧集来获取$ \ epsilon $ -optimal政策。我们的上限与依赖于$ \ epsilon $的依赖性和$ d $ if $ h \ ge d $。
translated by 谷歌翻译
This paper investigates conditions under which modi cations to the reward function of a Markov decision process preserve the optimal policy. It is shown that, besides the positive linear transformation familiar from utility theory, one can add a reward for transitions between states that is expressible as the di erence in value of an arbitrary potential function applied to those states. Furthermore, this is shown to be a necessary condition for invariance, in the sense that any other transformation may yield suboptimal policies unless further assumptions are made about the underlying MDP. These results shed light on the practice of reward shaping, a method used in reinforcement learning whereby additional training rewards are used to guide the learning agent. In particular, some well-known \bugs" in reward shaping procedures are shown to arise from non-potential-based rewards, and methods are given for constructing shaping potentials corresponding to distance-based and subgoalbased heuristics. We show that such potentials can lead to substantial reductions in learning time.
translated by 谷歌翻译
我们介绍了一种普遍的策略,可实现有效的多目标勘探。它依赖于adagoal,一种基于简单约束优化问题的新的目标选择方案,其自适应地针对目标状态,这既不是太困难也不是根据代理目前的知识达到的。我们展示了Adagoal如何用于解决学习$ \ epsilon $ -optimal的目标条件的政策,以便在$ L $ S_0 $ S_0 $奖励中获得的每一个目标状态,以便在$ S_0 $中获取。免费马尔可夫决策过程。在标准的表格外壳中,我们的算法需要$ \ tilde {o}(l ^ 3 s a \ epsilon ^ { - 2})$探索步骤,这几乎很少最佳。我们还容易在线性混合Markov决策过程中实例化Adagoal,其产生具有线性函数近似的第一目标导向的PAC保证。除了强大的理论保证之外,迈克纳队以现有方法的高级别算法结构为锚定,为目标条件的深度加固学习。
translated by 谷歌翻译
Modern Reinforcement Learning (RL) is commonly applied to practical problems with an enormous number of states, where function approximation must be deployed to approximate either the value function or the policy. The introduction of function approximation raises a fundamental set of challenges involving computational and statistical efficiency, especially given the need to manage the exploration/exploitation tradeoff. As a result, a core RL question remains open: how can we design provably efficient RL algorithms that incorporate function approximation? This question persists even in a basic setting with linear dynamics and linear rewards, for which only linear function approximation is needed.This paper presents the first provable RL algorithm with both polynomial runtime and polynomial sample complexity in this linear setting, without requiring a "simulator" or additional assumptions. Concretely, we prove that an optimistic modification of Least-Squares Value Iteration (LSVI)-a classical algorithm frequently studied in the linear setting-achieves O( √ d 3 H 3 T ) regret, where d is the ambient dimension of feature space, H is the length of each episode, and T is the total number of steps. Importantly, such regret is independent of the number of states and actions.
translated by 谷歌翻译
This work considers the sample complexity of obtaining an $\varepsilon$-optimal policy in an average reward Markov Decision Process (AMDP), given access to a generative model (simulator). When the ground-truth MDP is weakly communicating, we prove an upper bound of $\widetilde O(H \varepsilon^{-3} \ln \frac{1}{\delta})$ samples per state-action pair, where $H := sp(h^*)$ is the span of bias of any optimal policy, $\varepsilon$ is the accuracy and $\delta$ is the failure probability. This bound improves the best-known mixing-time-based approaches in [Jin & Sidford 2021], which assume the mixing-time of every deterministic policy is bounded. The core of our analysis is a proper reduction bound from AMDP problems to discounted MDP (DMDP) problems, which may be of independent interests since it allows the application of DMDP algorithms for AMDP in other settings. We complement our upper bound by proving a minimax lower bound of $\Omega(|\mathcal S| |\mathcal A| H \varepsilon^{-2} \ln \frac{1}{\delta})$ total samples, showing that a linear dependent on $H$ is necessary and that our upper bound matches the lower bound in all parameters of $(|\mathcal S|, |\mathcal A|, H, \ln \frac{1}{\delta})$ up to some logarithmic factors.
translated by 谷歌翻译
We develop an extension of posterior sampling for reinforcement learning (PSRL) that is suited for a continuing agent-environment interface and integrates naturally into agent designs that scale to complex environments. The approach maintains a statistically plausible model of the environment and follows a policy that maximizes expected $\gamma$-discounted return in that model. At each time, with probability $1-\gamma$, the model is replaced by a sample from the posterior distribution over environments. For a suitable schedule of $\gamma$, we establish an $\tilde{O}(\tau S \sqrt{A T})$ bound on the Bayesian regret, where $S$ is the number of environment states, $A$ is the number of actions, and $\tau$ denotes the reward averaging time, which is a bound on the duration required to accurately estimate the average reward of any policy.
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 $,这似乎是在此设置中使用样品复杂性保证的第一个结果。进行了不同的实验以证明我们的理论发现,显示了我们算法与非持bust算法的优越性。
translated by 谷歌翻译
强化学习算法的实用性由于相对于问题大小的规模差而受到限制,因为学习$ \ epsilon $ -optimal策略的样本复杂性为$ \ tilde {\ omega} \ left(| s | s || a || a || a || a | h^3 / \ eps^2 \ right)$在MDP的最坏情况下,带有状态空间$ S $,ACTION SPACE $ A $和HORIZON $ H $。我们考虑一类显示出低级结构的MDP,其中潜在特征未知。我们认为,价值迭代和低级别矩阵估计的自然组合导致估计误差在地平线上呈指数增长。然后,我们提供了一种新算法以及统计保证,即有效利用了对生成模型的访问,实现了$ \ tilde {o} \ left的样本复杂度(d^5(d^5(| s |+| a |)\),我们有效利用低级结构。对于等级$ d $设置的Mathrm {Poly}(h)/\ EPS^2 \ right)$,相对于$ | s |,| a | $和$ \ eps $的缩放,这是最小值的最佳。与线性和低级别MDP的文献相反,我们不需要已知的功能映射,我们的算法在计算上很简单,并且我们的结果长期存在。我们的结果提供了有关MDP对过渡内核与最佳动作值函数所需的最小低级结构假设的见解。
translated by 谷歌翻译
最近有兴趣了解地平线依赖于加固学习(RL)的样本复杂性。值得注意的是,对于具有Horizo​​ n长度$ H $的RL环境,之前的工作表明,使用$ \ mathrm {polylog}(h)有可能学习$ o(1)$ - 最佳策略的可能大致正确(pac)算法$当州和行动的数量固定时的环境交互剧集。它尚不清楚$ \ mathrm {polylog}(h)$依赖性是必要的。在这项工作中,我们通过开发一种算法来解决这个问题,该算法在仅使用ONTO(1)美元的环境交互的同时实现相同的PAC保证,完全解决RL中样本复杂性的地平线依赖性。我们通过(i)在贴现和有限地平线马尔可夫决策过程(MDP)和(ii)在MDP中的新型扰动分析中建立价值函数之间的联系。我们相信我们的新技术具有独立兴趣,可在RL中应用相关问题。
translated by 谷歌翻译
我们研究了在不确定的环境中运行的机器人面临的计划问题,对状态不完整,嘈杂和/或不精确的行动。本文确定了一个新的问题子类,该阶级模拟了设置信息,在该设置中,只有通过某些外源过程,该过程会间歇性地揭示信息,该过程定期提供状态信息。几个实用领域符合该模型,包括激发我们研究的特定情况:远程成像增强行星探索的自主导航。为了注视着有效的专业解决方案方法,我们检查了该子类实例的结构。它们导致马尔可夫的决策过程具有指数较大的动作空间,但由于这些动作包括更多原子元素的序列,因此可以通过比较不同信息假设下的策略来建立绩效界限。这提供了一种系统地构建性能界限的方法。这样的界限很有用,因为与它们赋予的见解结合在一起,它们可以采用基于边界的方法来有效地获得高质量的解决方案。我们提出的经验结果证明了它们对所考虑的问题的有效性。上述内容还提到了时间时间为这些问题所扮演的独特作用 - 更具体地说:直到信息揭示的时间 - 我们在这方面发现并讨论了几个有趣的微妙之处。
translated by 谷歌翻译
在最大的状态熵探索框架中,代理商与无奖励环境进行交互,以学习最大程度地提高其正在引起的预期国有访问的熵的政策。 Hazan等。 (2019年)指出,马尔可夫随机策略类别足以满足最大状态熵目标,而在这种情况下,利用非马克维亚性通常被认为是毫无意义的。在本文中,我们认为非马克维亚性是有限样本制度中最大状态熵探索至关重要的。尤其是,我们重新阐明了目标在一次试验中针对诱发的国有访问的预期熵的目标。然后,我们表明,非马克维亚确定性政策的类别足以满足引入的目标,而马尔可夫政策总体上遭受了非零的遗憾。但是,我们证明找到最佳的非马克维亚政策的问题是NP-HARD。尽管结果有负面的结果,但我们讨论了以一种可行的方式解决该问题的途径,以及非马克维亚探索如何使未来工作中在线增强学习的样本效率受益。
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
逆增强学习(IRL)是从专家演示中推断奖励功能的强大范式。许多IRL算法都需要已知的过渡模型,有时甚至是已知的专家政策,或者至少需要访问生成模型。但是,对于许多现实世界应用,这些假设太强了,在这些应用程序中,只能通过顺序相互作用访问环境。我们提出了一种新颖的IRL算法:逆增强学习(ACEIRL)的积极探索,该探索积极探索未知的环境和专家政策,以快速学习专家的奖励功能并确定良好的政策。 Aceirl使用以前的观察来构建置信区间,以捕获合理的奖励功能,并找到关注环境最有用区域的勘探政策。 Aceirl是使用样品复杂性界限的第一种活动IRL的方法,不需要环境的生成模型。在最坏情况下,Aceirl与活性IRL的样品复杂性与生成模型匹配。此外,我们建立了一个与问题相关的结合,该结合将Aceirl的样品复杂性与给定IRL问题的次级隔离间隙联系起来。我们在模拟中对Aceirl进行了经验评估,发现它的表现明显优于更幼稚的探索策略。
translated by 谷歌翻译
我们提出了一个新的学习框架,该框架捕获了许多真实世界用户交互应用程序的分层结构,在该框架中,可以根据探索风险的不同公差将用户分为两组,并应分别处理。在这种情况下,我们同时维护两个政策$ \ pi^{\ text {o}} $和$ \ pi^{\ text {e}} $:$ \ pi^{\ pi^{\ text {o}}} $(“ o “对于“在线”)与第一层的更具风险的用户进行互动,并像往常一样平衡探索和剥削来最大程度地减少后悔,而$ \ pi^{\ text {e}} $(“ e” for“ exploit”)专注于利用到目前为止收集的数据,从第二层的规避风险用户进行剥削。一个重要的问题是,这种分离是否比标准在线设置(即$ \ pi^{\ text {e}} = \ pi^{\ text {o}} $)是否产生优势。我们单独考虑与差距无关的与差距依赖性设置。对于前者来说,我们证明从最小值的角度来看,分离确实不是有益的。对于后者,我们表明,如果选择悲观的价值迭代作为剥削算法来产生$ \ pi^{\ text {e}} $,我们可以不断地对无独立的风险用户$ k的数量来实现遗憾$,与$ \ omega(\ log k)$相同的$ \ omega(\ log k)$在同一环境中遗憾在线遗憾的最优性,不需要为成功的成功而妥协。
translated by 谷歌翻译