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
策略梯度方法适用于复杂的,不理解的,通过对参数化的策略进行随机梯度下降来控制问题。不幸的是,即使对于可以通过标准动态编程技术解决的简单控制问题,策略梯度算法也会面临非凸优化问题,并且被广泛理解为仅收敛到固定点。这项工作确定了结构属性 - 通过几个经典控制问题共享 - 确保策略梯度目标函数尽管是非凸面,但没有次优的固定点。当这些条件得到加强时,该目标满足了产生收敛速率的Polyak-lojasiewicz(梯度优势)条件。当其中一些条件放松时,我们还可以在任何固定点的最佳差距上提供界限。
translated by 谷歌翻译
Reinforcement learning is a framework for interactive decision-making with incentives sequentially revealed across time without a system dynamics model. Due to its scaling to continuous spaces, we focus on policy search where one iteratively improves a parameterized policy with stochastic policy gradient (PG) updates. In tabular Markov Decision Problems (MDPs), under persistent exploration and suitable parameterization, global optimality may be obtained. By contrast, in continuous space, the non-convexity poses a pathological challenge as evidenced by existing convergence results being mostly limited to stationarity or arbitrary local extrema. To close this gap, we step towards persistent exploration in continuous space through policy parameterizations defined by distributions of heavier tails defined by tail-index parameter alpha, which increases the likelihood of jumping in state space. Doing so invalidates smoothness conditions of the score function common to PG. Thus, we establish how the convergence rate to stationarity depends on the policy's tail index alpha, a Holder continuity parameter, integrability conditions, and an exploration tolerance parameter introduced here for the first time. Further, we characterize the dependence of the set of local maxima on the tail index through an exit and transition time analysis of a suitably defined Markov chain, identifying that policies associated with Levy Processes of a heavier tail converge to wider peaks. This phenomenon yields improved stability to perturbations in supervised learning, which we corroborate also manifests in improved performance of policy search, especially when myopic and farsighted incentives are misaligned.
translated by 谷歌翻译
为了在许多因素动态影响输出轨迹的复杂随机系统上学习,希望有效利用从以前迭代中收集的历史样本中的信息来加速策略优化。经典的经验重播使代理商可以通过重复使用历史观察来记住。但是,处理所有观察结果的统一重复使用策略均忽略了不同样本的相对重要性。为了克服这一限制,我们提出了一个基于一般差异的经验重播(VRER)框架,该框架可以选择性地重复使用最相关的样本以改善策略梯度估计。这种选择性机制可以自适应地对过去的样品增加重量,这些样本更可能由当前目标分布产生。我们的理论和实证研究表明,提议的VRER可以加速学习最佳政策,并增强最先进的政策优化方法的性能。
translated by 谷歌翻译
为了在许多因素动态影响输出轨迹的复杂随机系统上学习,希望有效利用从以前迭代中收集的历史样本中的信息来加速策略优化。经典的经验重播使代理商可以通过重复使用历史观察来记住。但是,处理所有观察结果的统一重复使用策略均忽略了不同样本的相对重要性。为了克服这一限制,我们提出了一个基于一般差异的经验重播(VRER)框架,该框架可以选择性地重复使用最相关的样本以改善策略梯度估计。这种选择性机制可以自适应地对过去的样品增加重量,这些样本更可能由当前目标分布产生。我们的理论和实证研究表明,提议的VRER可以加速学习最佳政策,并增强最先进的政策优化方法的性能。
translated by 谷歌翻译
我们改进了用于分析非凸优化随机梯度下降(SGD)的最新工具,以获得香草政策梯度(PG) - 加强和GPOMDP的收敛保证和样本复杂性。我们唯一的假设是预期回报是平滑的w.r.t.策略参数以及其渐变的第二个时刻满足某种\ EMPH {ABC假设}。 ABC的假设允许梯度的第二时刻绑定为\ geq 0 $次的子项优差距,$ b \ geq 0 $乘以完整批量梯度的标准和添加剂常数$ c \ geq 0 $或上述任何组合。我们表明ABC的假设比策略空间上的常用假设更为一般,以证明收敛到静止点。我们在ABC的假设下提供单个融合定理,并表明,尽管ABC假设的一般性,我们恢复了$ \ widetilde {\ mathcal {o}}(\ epsilon ^ {-4})$样本复杂性pg 。我们的融合定理还可在选择超参数等方面提供更大的灵活性,例如步长和批量尺寸的限制$ M $。即使是单个轨迹案例(即,$ M = 1 $)适合我们的分析。我们认为,ABC假设的一般性可以为PG提供理论担保,以至于以前未考虑的更广泛的问题。
translated by 谷歌翻译
当我们不允许我们使用目标策略进行采样,而只能访问某些未知行为策略生成的数据集时,策略梯度(PG)估计就成为一个挑战。用于支付政策PG估计的常规方法通常会遭受明显的偏差或指数较大的差异。在本文中,我们提出了双拟合的PG估计(FPG)算法。假设访问Bellman-Complete值函数类,FPG可以与任意策略参数化一起工作。在线性值函数近似的情况下,我们在策略梯度估计误差上提供了一个紧密的有限样本上限,该界限受特征空间中测量的分布不匹配量的控制。我们还建立了FPG估计误差的渐近正态性,并具有精确的协方差表征,这进一步证明在统计上是最佳的,具有匹配的Cramer-Rao下限。从经验上讲,我们使用SoftMax表格或RELU策略网络评估FPG在策略梯度估计和策略优化方面的性能。在各种指标下,我们的结果表明,基于重要性采样和降低方差技术,FPG显着优于现有的非政策PG估计方法。
translated by 谷歌翻译
In this paper we develop a theoretical analysis of the performance of sampling-based fitted value iteration (FVI) to solve infinite state-space, discounted-reward Markovian decision processes (MDPs) under the assumption that a generative model of the environment is available. Our main results come in the form of finite-time bounds on the performance of two versions of sampling-based FVI. The convergence rate results obtained allow us to show that both versions of FVI are well behaving in the sense that by using a sufficiently large number of samples for a large class of MDPs, arbitrary good performance can be achieved with high probability. An important feature of our proof technique is that it permits the study of weighted L p -norm performance bounds. As a result, our technique applies to a large class of function-approximation methods (e.g., neural networks, adaptive regression trees, kernel machines, locally weighted learning), and our bounds scale well with the effective horizon of the MDP. The bounds show a dependence on the stochastic stability properties of the MDP: they scale with the discounted-average concentrability of the future-state distributions. They also depend on a new measure of the approximation power of the function space, the inherent Bellman residual, which reflects how well the function space is "aligned" with the dynamics and rewards of the MDP. The conditions of the main result, as well as the concepts introduced in the analysis, are extensively discussed and compared to previous theoretical results. Numerical experiments are used to substantiate the theoretical findings.
translated by 谷歌翻译
在本文中,我们研究了加强学习问题的安全政策的学习。这是,我们的目标是控制我们不知道过渡概率的马尔可夫决策过程(MDP),但我们通过经验访问样品轨迹。我们将安全性定义为在操作时间内具有高概率的期望安全集中的代理。因此,我们考虑受限制的MDP,其中限制是概率。由于没有直接的方式来优化关于加强学习框架中的概率约束的政策,因此我们提出了对问题的遍历松弛。拟议的放松的优点是三倍。 (i)安全保障在集界任务的情况下保持,并且它们保持在一个给定的时间范围内,以继续进行任务。 (ii)如果政策的参数化足够丰富,则约束优化问题尽管其非凸起具有任意小的二元间隙。 (iii)可以使用标准策略梯度结果和随机近似工具容易地计算与安全学习问题相关的拉格朗日的梯度。利用这些优势,我们建立了原始双算法能够找到安全和最佳的政策。我们在连续域中的导航任务中测试所提出的方法。数值结果表明,我们的算法能够将策略动态调整到环境和所需的安全水平。
translated by 谷歌翻译
In many sequential decision-making problems one is interested in minimizing an expected cumulative cost while taking into account risk, i.e., increased awareness of events of small probability and high consequences. Accordingly, the objective of this paper is to present efficient reinforcement learning algorithms for risk-constrained Markov decision processes (MDPs), where risk is represented via a chance constraint or a constraint on the conditional value-at-risk (CVaR) of the cumulative cost. We collectively refer to such problems as percentile risk-constrained MDPs. Specifically, we first derive a formula for computing the gradient of the Lagrangian function for percentile riskconstrained MDPs. Then, we devise policy gradient and actor-critic algorithms that (1) estimate such gradient, (2) update the policy in the descent direction, and (3) update the Lagrange multiplier in the ascent direction. For these algorithms we prove convergence to locally optimal policies. Finally, we demonstrate the effectiveness of our algorithms in an optimal stopping problem and an online marketing application.
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
我们研究了用线性函数近似的加固学习中的违规评估(OPE)问题,旨在根据行为策略收集的脱机数据来估计目标策略的价值函数。我们建议纳入价值函数的方差信息以提高ope的样本效率。更具体地说,对于时间不均匀的epiSodic线性马尔可夫决策过程(MDP),我们提出了一种算法VA-OPE,它使用价值函数的估计方差重新重量拟合Q迭代中的Bellman残差。我们表明我们的算法达到了比最着名的结果绑定的更紧密的误差。我们还提供了行为政策与目标政策之间的分布转移的细粒度。广泛的数值实验证实了我们的理论。
translated by 谷歌翻译
在线强化学习(RL)中的挑战之一是代理人需要促进对环境的探索和对样品的利用来优化其行为。无论我们是否优化遗憾,采样复杂性,状态空间覆盖范围或模型估计,我们都需要攻击不同的勘探开发权衡。在本文中,我们建议在分离方法组成的探索 - 剥削问题:1)“客观特定”算法(自适应)规定哪些样本以收集到哪些状态,似乎它可以访问a生成模型(即环境的模拟器); 2)负责尽可能快地生成规定样品的“客观无关的”样品收集勘探策略。建立最近在随机最短路径问题中进行探索的方法,我们首先提供一种算法,它给出了每个状态动作对所需的样本$ B(S,a)$的样本数量,需要$ \ tilde {o} (bd + d ^ {3/2} s ^ 2 a)收集$ b = \ sum_ {s,a} b(s,a)$所需样本的$时间步骤,以$ s $各国,$ a $行动和直径$ d $。然后我们展示了这种通用探索算法如何与“客观特定的”策略配对,这些策略规定了解决各种设置的样本要求 - 例如,模型估计,稀疏奖励发现,无需无成本勘探沟通MDP - 我们获得改进或新颖的样本复杂性保证。
translated by 谷歌翻译
We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. Focusing on a stochastic query model that provides noisy evaluations of the operator, we analyze a variance-reduced stochastic approximation scheme, and establish non-asymptotic bounds for both the operator defect and the estimation error, measured in an arbitrary semi-norm. In contrast to worst-case guarantees, our bounds are instance-dependent, and achieve the local asymptotic minimax risk non-asymptotically. For linear operators, contractivity can be relaxed to multi-step contractivity, so that the theory can be applied to problems like average reward policy evaluation problem in reinforcement learning. We illustrate the theory via applications to stochastic shortest path problems, two-player zero-sum Markov games, as well as policy evaluation and $Q$-learning for tabular Markov decision processes.
translated by 谷歌翻译
本文分析了双模的彼此优化随机算法框架。 Bilevel优化是一类表现出两级结构的问题,其目标是使具有变量的外目标函数最小化,该变量被限制为对(内部)优化问题的最佳解决方案。我们考虑内部问题的情况是不受约束的并且强烈凸起的情况,而外部问题受到约束并具有平滑的目标函数。我们提出了一种用于解决如此偏纤维问题的两次时间尺度随机近似(TTSA)算法。在算法中,使用较大步长的随机梯度更新用于内部问题,而具有较小步长的投影随机梯度更新用于外部问题。我们在各种设置下分析了TTSA算法的收敛速率:当外部问题强烈凸起(RESP。〜弱凸)时,TTSA算法查找$ \ MATHCAL {O}(k ^ { - 2/3})$ -Optimal(resp。〜$ \ mathcal {o}(k ^ {-2/5})$ - 静止)解决方案,其中$ k $是总迭代号。作为一个应用程序,我们表明,两个时间尺度的自然演员 - 批评批评近端策略优化算法可以被视为我们的TTSA框架的特殊情况。重要的是,与全球最优政策相比,自然演员批评算法显示以预期折扣奖励的差距,以$ \ mathcal {o}(k ^ { - 1/4})的速率收敛。
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
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
由于策略梯度定理导致的策略设置存在各种理论上 - 声音策略梯度算法,其为梯度提供了简化的形式。然而,由于存在多重目标和缺乏明确的脱助政策政策梯度定理,截止策略设置不太明确。在这项工作中,我们将这些目标统一到一个违规目标,并为此统一目标提供了政策梯度定理。推导涉及强调的权重和利息职能。我们显示多种策略来近似梯度,以识别权重(ACE)称为Actor评论家的算法。我们证明了以前(半梯度)脱离政策演员 - 评论家 - 特别是offpac和DPG - 收敛到错误的解决方案,而Ace找到最佳解决方案。我们还强调为什么这些半梯度方法仍然可以在实践中表现良好,表明ace中的方差策略。我们经验研究了两个经典控制环境的若干ACE变体和基于图像的环境,旨在说明每个梯度近似的权衡。我们发现,通过直接逼近强调权重,ACE在所有测试的所有设置中执行或优于offpac。
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
我们在无限地平线马尔可夫决策过程中考虑批量(离线)策略学习问题。通过移动健康应用程序的推动,我们专注于学习最大化长期平均奖励的政策。我们为平均奖励提出了一款双重强大估算器,并表明它实现了半导体效率。此外,我们开发了一种优化算法来计算参数化随机策略类中的最佳策略。估计政策的履行是通过政策阶级的最佳平均奖励与估计政策的平均奖励之间的差异来衡量,我们建立了有限样本的遗憾保证。通过模拟研究和促进体育活动的移动健康研究的分析来说明该方法的性能。
translated by 谷歌翻译