We propose a new policy gradient method, named homotopic policy mirror descent (HPMD), for solving discounted, infinite horizon MDPs with finite state and action spaces. HPMD performs a mirror descent type policy update with an additional diminishing regularization term, and possesses several computational properties that seem to be new in the literature. We first establish the global linear convergence of HPMD instantiated with Kullback-Leibler divergence, for both the optimality gap, and a weighted distance to the set of optimal policies. Then local superlinear convergence is obtained for both quantities without any assumption. With local acceleration and diminishing regularization, we establish the first result among policy gradient methods on certifying and characterizing the limiting policy, by showing, with a non-asymptotic characterization, that the last-iterate policy converges to the unique optimal policy with the maximal entropy. We then extend all the aforementioned results to HPMD instantiated with a broad class of decomposable Bregman divergences, demonstrating the generality of the these computational properties. As a by product, we discover the finite-time exact convergence for some commonly used Bregman divergences, implying the continuing convergence of HPMD to the limiting policy even if the current policy is already optimal. Finally, we develop a stochastic version of HPMD and establish similar convergence properties. By exploiting the local acceleration, we show that for small optimality gap, a better than $\tilde{\mathcal{O}}(\left|\mathcal{S}\right| \left|\mathcal{A}\right| / \epsilon^2)$ sample complexity holds with high probability, when assuming a generative model for policy evaluation.
translated by 谷歌翻译
在本文中,我们提出了一种新的策略梯度(PG)方法,即用于解决一类正规化加固学习(RL)问题的块策略镜下降(BPMD)方法(强烈) - convex正规化器。与带有批处理更新规则的传统PG方法(访问和更新每个状态的策略)相比,BPMD方法通过部分更新规则具有廉价的每卷计算,该规则在采样状态上执行策略更新。尽管问题的性质和部分更新规则具有非概念性质,但我们还是为多种采样方案提供了统一的分析,并表明BPMD可以实现快速的线性收敛到全局最优性。特别是,均匀的采样导致可比的最坏情况总计算复杂性与批处理PG方法。还确定了一种与上policy采样的必要条件。通过混合采样方案,我们进一步表明,BPMD具有潜在的实例依赖性加速度,从而改善了对状态空间的依赖性,因此优于批次PG方法。然后,我们通过利用从样品构建的随机一阶信息扩展到随机设置。使用生成模型,$ \ tilde {\ mathcal {o}}(\ left \ lvert \ lerver \ mathcal {s} \ right \ rvert \ rvert \ left \ lest \ lerver \ lovt \ mathcal {a} \ right \ right \ rvert \ rvert \ rvert /\ epsilon) $ \ tilde {\ mathcal {o}}(\ left \ lvert \ m athcal {s} \ right \ rvert \ rvert \ left \ lest \ lvert \ lerver \ mathcal {a} \ right \ right \ rvert /\ epsilon^2)强率强度(分别为非巧克力符号)正规化器,其中$ \ epsilon $表示目标准确性。据我们所知,这是第一次开发和分析了块坐标下降方法,以进行强化学习的策略优化,这为解决大规模RL问题提供了新的观点。
translated by 谷歌翻译
我们考虑解决强大的马尔可夫决策过程(MDP)的问题,该过程涉及一组折扣,有限状态,有限的动作空间MDP,具有不确定的过渡核。计划的目的是找到一项强大的政策,以优化针对过渡不确定性的最坏情况值,从而将标准MDP计划作为特殊情况。对于$(\ Mathbf {s},\ Mathbf {a})$ - 矩形不确定性集,我们开发了一种基于策略的一阶方法,即稳健的策略镜像下降(RPMD),并建立$ \ Mathcal {o }(\ log(1/\ epsilon))$和$ \ Mathcal {o}(1/\ epsilon)$迭代复杂性,用于查找$ \ epsilon $ -optimal策略,并带有两个增加的步骤式方案。 RPMD的先前收敛适用于任何Bregman差异,前提是政策空间在以初始政策为中心时通过差异测量的半径限制了半径。此外,当布雷格曼的分歧对应于平方的欧几里得距离时,我们建立了一个$ \ mathcal {o}(\ max \ {1/\ epsilon,1/(\ eta \ eTa \ epsilon^2)\ epsilon^2)\任何常量的步进$ \ eta $。对于Bregman差异的一般类别,如果不确定性集满足相对强的凸度,则还为RPMD建立了类似的复杂性。当仅通过与名义环境的在线互动获得一阶信息时,我们进一步开发了一个名为SRPMD的随机变体。对于Bregman General Divergences,我们建立了一个$ \ MATHCAL {O}(1/\ Epsilon^2)$和$ \ Mathcal {O}(1/\ Epsilon^3)$样品复杂性,具有两个增加的静态方案。对于Euclidean Bregman Divergence,我们建立了一个$ \ MATHCAL {O}(1/\ Epsilon^3)$样本复杂性,并具有恒定的步骤。据我们所知,所有上述结果似乎是应用于强大的MDP问题的基于策略的一阶方法的新事物。
translated by 谷歌翻译
我们研究了平均奖励马尔可夫决策过程(AMDP)的问题,并开发了具有强大理论保证的新型一阶方法,以进行政策评估和优化。由于缺乏勘探,现有的彻底评估方法遭受了次优融合率以及处理不足的随机策略(例如确定性政策)的失败。为了解决这些问题,我们开发了一种新颖的差异时间差异(VRTD)方法,具有随机策略的线性函数近似以及最佳收敛保证,以及一种探索性方差降低的时间差(EVRTD)方法,用于不充分的随机策略,可相当的融合保证。我们进一步建立了政策评估偏见的线性收敛速率,这对于改善策略优化的总体样本复杂性至关重要。另一方面,与对MDP的政策梯度方法的有限样本分析相比,对AMDP的策略梯度方法的现有研究主要集中在基础马尔可夫流程的限制性假设下(例如,参见Abbasi-e, Yadkori等人,2019年),他们通常缺乏整体样本复杂性的保证。为此,我们开发了随机策略镜下降(SPMD)的平均奖励变体(LAN,2022)。我们建立了第一个$ \ widetilde {\ Mathcal {o}}(\ epsilon^{ - 2})$样品复杂性,用于在生成模型(带有UNICHAIN假设)和Markovian Noise模型(使用Ergodicicic Modele(具有核能的模型)下,使用策略梯度方法求解AMDP假设)。该界限可以进一步改进到$ \ widetilde {\ Mathcal {o}}}(\ epsilon^{ - 1})$用于求解正则化AMDPS。我们的理论优势通过数值实验来证实。
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
The softmax policy gradient (PG) method, which performs gradient ascent under softmax policy parameterization, is arguably one of the de facto implementations of policy optimization in modern reinforcement learning. For $\gamma$-discounted infinite-horizon tabular Markov decision processes (MDPs), remarkable progress has recently been achieved towards establishing global convergence of softmax PG methods in finding a near-optimal policy. However, prior results fall short of delineating clear dependencies of convergence rates on salient parameters such as the cardinality of the state space $\mathcal{S}$ and the effective horizon $\frac{1}{1-\gamma}$, both of which could be excessively large. In this paper, we deliver a pessimistic message regarding the iteration complexity of softmax PG methods, despite assuming access to exact gradient computation. Specifically, we demonstrate that the softmax PG method with stepsize $\eta$ can take \[ \frac{1}{\eta} |\mathcal{S}|^{2^{\Omega\big(\frac{1}{1-\gamma}\big)}} ~\text{iterations} \] to converge, even in the presence of a benign policy initialization and an initial state distribution amenable to exploration (so that the distribution mismatch coefficient is not exceedingly large). This is accomplished by characterizing the algorithmic dynamics over a carefully-constructed MDP containing only three actions. Our exponential lower bound hints at the necessity of carefully adjusting update rules or enforcing proper regularization in accelerating PG methods.
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
政策优化,通过大规模优化技术最大化价值函数来学习兴趣的政策,位于现代强化学习(RL)的核心。除了价值最大化之外,其他实际考虑因素也出现,包括令人鼓舞的探索,以及确保由于安全,资源和运营限制而确保学习政策的某些结构性。这些考虑通常可以通过诉诸正规化的RL来占据,这增加了目标值函数,并通过结构促进正则化术语。专注于无限范围打折马尔可夫决策过程,本文提出了一种用于解决正规化的RL的广义策略镜血压(GPMD)算法。作为策略镜血压LAN的概括(2021),所提出的算法可以容纳一般类凸常规的常规阶级,以及在使用中的规则器的认识到的广泛的Bregman分歧。我们展示了我们的算法在整个学习速率范围内,以无维的方式在全球解决方案的整个学习速率范围内融合到全球解决方案,即使常规器缺乏强大的凸起和平滑度。此外,在不精确的策略评估和不完美的政策更新方面,该线性收敛特征是可透明的。提供数值实验以证实GPMD的适用性和吸引力性能。
translated by 谷歌翻译
BREGMAN近端点算法(BPPA)是优化工具箱中的核心之一,一直在目睹新兴应用程序。通过简单易于实现更新规则,该算法对实证成功进行了几种引人注目的直觉,但严格的理由仍然很大程度上是未开发的。我们通过具有可分离数据的分类任务研究BPPA的计算属性,并证明与BPPA相关的可提供算法正则化效果。我们表明BPPA达到了非平凡的余量,这密切依赖于诱导BREGMAN发散的距离产生功能的条件数。我们进一步证明,对于一类问题,对条件数量的依赖性是紧张的,从而表明发散在影响所获得的解决方案的质量方面的重要性。此外,我们还将我们的调查结果扩展到镜像血统(MD),我们建立了边缘和BREGMAN发散之间的类似联系。我们通过具体示例演示,并显示BPPA / MD在相对于Mahalanobis距离的最大边缘解决方案方向上会聚。我们的理论调查结果是第一个展示良性学习特性BPPA / MD的态度,并且还提供校正算法设计中仔细选择的腐败。
translated by 谷歌翻译
Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This prevents the application of many well-studied RL methods especially those with provable convergence guarantees. In this paper, we first present a substantial generalization of the recently developed policy mirror descent method to deal with general state and action spaces. We introduce new approaches to incorporate function approximation into this method, so that we do not need to use explicit policy parameterization at all. Moreover, we present a novel policy dual averaging method for which possibly simpler function approximation techniques can be applied. We establish linear convergence rate to global optimality or sublinear convergence to stationarity for these methods applied to solve different classes of RL problems under exact policy evaluation. We then define proper notions of the approximation errors for policy evaluation and investigate their impact on the convergence of these methods applied to general-state RL problems with either finite-action or continuous-action spaces. To the best of our knowledge, the development of these algorithmic frameworks as well as their convergence analysis appear to be new in the literature.
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
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
We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of their entropy-regularized long-term rewards. To overcome the curse of dimensionality and to reduce communication, we propose a Localized Policy Iteration (LPI) algorithm that provably learns a near-globally-optimal policy using only local information. In particular, we show that, despite restricting each agent's attention to only its $\kappa$-hop neighborhood, the agents are able to learn a policy with an optimality gap that decays polynomially in $\kappa$. In addition, we show the finite-sample convergence of LPI to the global optimal policy, which explicitly captures the trade-off between optimality and computational complexity in choosing $\kappa$. Numerical simulations demonstrate the effectiveness of LPI.
translated by 谷歌翻译
Q-Learning,旨在以无模式的方式学习Markov决策过程(MDP)的最佳Q函数,位于加强学习的核心。当涉及到同步设置时(从每次迭代中从生成模型中从生成模型中汲取独立样本)时,已经对理解Q学习的样本效率进行了实质性进展。考虑一个$ \ gamma $ -discounted infinite-horizo​​ n mdp与状态空间$ \ mathcal {s} $和动作空间$ \ mathcal {a} $:要产生一个entrywise $ \ varepsilon $ - 最佳q函数的克制,最先进的Q-Learning理论需要超出$ \ FRAC {| \ Mathcal {s} || \ mathcal {a} || \ {(1- \ gamma)^ 5 \ varepsilon的示例大小^ {2}} $,它无法匹配现有的最低限度下限。这引起了自然问题:Q-Learning的急剧性复杂性是什么?是Q-Learning可怕的次优吗?本文为同步设置解决了这些问题:(1)当$ | \ mathcal {a} | = 1 $(使q学习减少到TD学习)时,我们证明了TD学习的样本复杂性是最佳的最佳和尺度为$ \ frac {| \ mathcal {s} |} {(1- \ gamma)^ 3 \ varepsilon ^ 2} $(最多到日志系数); (2)当$ | \ mathcal {a} | \ geq 2 $时,我们解决了q-learning的样本复杂性,按$ \ frac {| \ mathcal {s} || \ mathcal {a} || } {(1- \ gamma)^ 4 \ varepsilon ^ 2} $(最多到日志系数)。我们的理论推出了Q-Leature的严格次优,当$ | \ mathcal {a} | \ geq 2 $,并严格严格估计在q-learning中的负面影响。最后,我们扩展了我们的分析以适应异步Q-Learning(即,与马尔可夫样本的情况),锐化其样本复杂性的地平线依赖性为$ \ frac {1} {(1- \ gamma)^ 4} $。
translated by 谷歌翻译
我们研究了情节块MDP中模型估计和无奖励学习的问题。在这些MDP中,决策者可以访问少数潜在状态产生的丰富观察或上下文。我们首先对基于固定行为策略生成的数据估算潜在状态解码功能(从观测到潜在状态的映射)感兴趣。我们在估计此功能的错误率上得出了信息理论的下限,并提出了接近此基本限制的算法。反过来,我们的算法还提供了MDP的所有组件的估计值。然后,我们研究在无奖励框架中学习近乎最佳政策的问题。根据我们有效的模型估计算法,我们表明我们可以以最佳的速度推断出策略(随着收集样品的数量增长大)的最佳策略。有趣的是,我们的分析提供了必要和充分的条件,在这些条件下,利用块结构可以改善样本复杂性,以识别近乎最佳的策略。当满足这些条件时,Minimax无奖励设置中的样本复杂性将通过乘法因子$ n $提高,其中$ n $是可能的上下文数量。
translated by 谷歌翻译
作为安全加强学习的重要框架,在最近的文献中已经广泛研究了受约束的马尔可夫决策过程(CMDP)。然而,尽管在各种式学习设置下取得了丰富的结果,但就算法设计和信息理论样本复杂性下限而言,仍然缺乏对离线CMDP问题的基本理解。在本文中,我们专注于仅在脱机数据可用的情况下解决CMDP问题。通过采用单极浓缩系数$ c^*$的概念,我们建立了一个$ \ omega \ left(\ frac {\ min \ left \ left \ weft \ {| \ mathcal {s} || \ mathcal {a} a} |,, | \ Mathcal {s} |+i \ right \} c^*} {(1- \ gamma)^3 \ epsilon^2} \ right)$ sample Complacy度在离线cmdp问题上,其中$ i $架对于约束数量。通过引入一种简单但新颖的偏差控制机制,我们提出了一种称为DPDL的近乎最佳的原始二重学习算法。该算法证明,除了$ \ tilde {\ Mathcal {o}}}}(((1- \ gamma)^{ - 1})$外,该算法可确保零约束违规及其样本复杂性匹配上下界。还包括有关如何处理未知常数$ c^*$以及离线数据集中潜在的异步结构的全面讨论。
translated by 谷歌翻译
We revisit the domain of off-policy policy optimization in RL from the perspective of coordinate ascent. One commonly-used approach is to leverage the off-policy policy gradient to optimize a surrogate objective -- the total discounted in expectation return of the target policy with respect to the state distribution of the behavior policy. However, this approach has been shown to suffer from the distribution mismatch issue, and therefore significant efforts are needed for correcting this mismatch either via state distribution correction or a counterfactual method. In this paper, we rethink off-policy learning via Coordinate Ascent Policy Optimization (CAPO), an off-policy actor-critic algorithm that decouples policy improvement from the state distribution of the behavior policy without using the policy gradient. This design obviates the need for distribution correction or importance sampling in the policy improvement step of off-policy policy gradient. We establish the global convergence of CAPO with general coordinate selection and then further quantify the convergence rates of several instances of CAPO with popular coordinate selection rules, including the cyclic and the randomized variants of CAPO. We then extend CAPO to neural policies for a more practical implementation. Through experiments, we demonstrate that CAPO provides a competitive approach to RL in practice.
translated by 谷歌翻译
我们研究具有多个奖励价值函数的马尔可夫决策过程(MDP)的政策优化,应根据给定的标准共同优化,例如比例公平(平滑凹面标量),硬约束(约束MDP)和Max-Min Trade-离开。我们提出了一个改变锚定的正规自然政策梯度(ARNPG)框架,该框架可以系统地将良好表现的一阶方法中的思想纳入多目标MDP问题的策略优化算法的设计。从理论上讲,基于ARNPG框架的设计算法实现了$ \ tilde {o}(1/t)$全局收敛,并具有精确的梯度。从经验上讲,与某些现有的基于策略梯度的方法相比,ARNPG引导的算法在精确梯度和基于样本的场景中也表现出卓越的性能。
translated by 谷歌翻译
Mean-field games have been used as a theoretical tool to obtain an approximate Nash equilibrium for symmetric and anonymous $N$-player games in literature. However, limiting applicability, existing theoretical results assume variations of a "population generative model", which allows arbitrary modifications of the population distribution by the learning algorithm. Instead, we show that $N$ agents running policy mirror ascent converge to the Nash equilibrium of the regularized game within $\tilde{\mathcal{O}}(\varepsilon^{-2})$ samples from a single sample trajectory without a population generative model, up to a standard $\mathcal{O}(\frac{1}{\sqrt{N}})$ error due to the mean field. Taking a divergent approach from literature, instead of working with the best-response map we first show that a policy mirror ascent map can be used to construct a contractive operator having the Nash equilibrium as its fixed point. Next, we prove that conditional TD-learning in $N$-agent games can learn value functions within $\tilde{\mathcal{O}}(\varepsilon^{-2})$ time steps. These results allow proving sample complexity guarantees in the oracle-free setting by only relying on a sample path from the $N$ agent simulator. Furthermore, we demonstrate that our methodology allows for independent learning by $N$ agents with finite sample guarantees.
translated by 谷歌翻译