基于模型的强化学习引起了广泛的样本效率。尽管到目前为止,它令人印象深刻,但仍然不清楚如何适当安排重要的超参数,以实现足够的性能,例如基于Dyna样式的算法中的政策优化的实际数据比。在本文中,我们首先分析了实际数据在政策培训中的作用,这表明逐渐增加了实际数据的比例会产生更好的性能。灵感来自分析,我们提出了一个名为autombpo的框架,以自动安排真实的数据比以及基于培训模型的策略优化(MBPO)算法的其他超参数,是基于模型的方法的代表性运行情况。在几个连续控制任务上,由AutomBPO安排的HyperParameters培训的MBPO实例可以显着超越原始的,并且AutomBPO找到的真实数据比例计划显示了与我们的理论分析的一致性。
translated by 谷歌翻译
Designing and analyzing model-based RL (MBRL) algorithms with guaranteed monotonic improvement has been challenging, mainly due to the interdependence between policy optimization and model learning. Existing discrepancy bounds generally ignore the impacts of model shifts, and their corresponding algorithms are prone to degrade performance by drastic model updating. In this work, we first propose a novel and general theoretical scheme for a non-decreasing performance guarantee of MBRL. Our follow-up derived bounds reveal the relationship between model shifts and performance improvement. These discoveries encourage us to formulate a constrained lower-bound optimization problem to permit the monotonicity of MBRL. A further example demonstrates that learning models from a dynamically-varying number of explorations benefit the eventual returns. Motivated by these analyses, we design a simple but effective algorithm CMLO (Constrained Model-shift Lower-bound Optimization), by introducing an event-triggered mechanism that flexibly determines when to update the model. Experiments show that CMLO surpasses other state-of-the-art methods and produces a boost when various policy optimization methods are employed.
translated by 谷歌翻译
提高强化学习样本效率的一种有希望的方法是基于模型的方法,其中在学习模型中可以进行许多探索和评估以节省现实世界样本。但是,当学习模型具有不可忽略的模型误差时,很难准确评估模型中的顺序步骤,从而限制了模型的利用率。本文建议通过引入多步计划来替换基于模型的RL的多步骤操作来减轻此问题。我们采用多步计划价值估计,该估计在执行给定状态的一系列操作计划后评估预期的折扣收益,并通过直接通过计划价值估计来直接计算多步策略梯度来更新策略。新的基于模型的强化学习算法MPPVE(基于模型的计划策略学习具有多步计划价值估计)显示了对学习模型的利用率更好,并且比基于ART模型的RL更好地实现了样本效率方法。
translated by 谷歌翻译
强化学习(RL)通过与环境相互作用的试验过程解决顺序决策问题。尽管RL在玩复杂的视频游戏方面取得了巨大的成功,但在现实世界中,犯错误总是不希望的。为了提高样本效率并从而降低错误,据信基于模型的增强学习(MBRL)是一个有前途的方向,它建立了环境模型,在该模型中可以进行反复试验,而无需实际成本。在这项调查中,我们对MBRL进行了审查,重点是Deep RL的最新进展。对于非壮观环境,学到的环境模型与真实环境之间始终存在概括性错误。因此,非常重要的是分析环境模型中的政策培训与实际环境中的差异,这反过来又指导了更好的模型学习,模型使用和政策培训的算法设计。此外,我们还讨论了其他形式的RL,包括离线RL,目标条件RL,多代理RL和Meta-RL的最新进展。此外,我们讨论了MBRL在现实世界任务中的适用性和优势。最后,我们通过讨论MBRL未来发展的前景来结束这项调查。我们认为,MBRL在被忽略的现实应用程序中具有巨大的潜力和优势,我们希望这项调查能够吸引更多关于MBRL的研究。
translated by 谷歌翻译
设计有效的基于模型的增强学习算法很困难,因为必须对模型生成数据的偏置权衡数据生成的易用性。在本文中,我们研究了模型使用在理论上和经验上的政策优化中的作用。我们首先制定和分析一种基于模型的加强学习算法,并在每个步骤中保证单调改善。在实践中,该分析过于悲观,并表明实际的脱助策略数据总是优选模拟策略数据,但我们表明可以将模型概括的经验估计纳入这样的分析以证明模型使用证明模型使用。通过这种分析的动机,我们证明,使用从真实数据分支的短模型生成的卷展栏的简单过程具有更复杂的基于模型的算法而没有通常的缺陷的效益。特别是,这种方法超越了基于模型的方法的样本效率,匹配了最佳无模型算法的渐近性能,并缩放到导致其他基于模型的方法完全失败的视野。
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
基于模型的增强学习(RL)通过学习动态模型来生成用于策略学习的样本,在实践中实现了实践中的样本效率更高。先前的作品学习了一个“全球”动力学模型,以适合所有历史政策的国家行动探视分布。但是,在本文中,我们发现学习全球动力学模型并不一定会受益于当前策略的模型预测,因为使用的策略正在不断发展。培训期间不断发展的政策将导致州行动探访分配变化。我们理论上分析了历史政策的分布如何影响模型学习和模型推出。然后,我们提出了一种基于模型的新型RL方法,名为\ textit {策略适应模型基于contor-Critic(PMAC)},该方法基于策略适应机制学习了一个基于策略适应的动力学模型。该机制会动态调整历史政策混合分布,以确保学习模型可以不断适应不断发展的政策的国家行动探视分布。在Mujoco中的一系列连续控制环境上进行的实验表明,PMAC可以实现最新的渐近性能,而样品效率几乎是基于模型的方法的两倍。
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
代表学习呈现在深入学习的经验成功的核心,以处理维度的诅咒。然而,由于i),表现力(RL)的钢筋学习(RL)尚未充分利用卓越的能力,表现力和易疏忽之间的权衡;二世),探索与代表学习之间的耦合。在本文中,我们首先揭示了在随机控制模型中的一些噪声假设下,我们可以免费获得其相应的马尔可夫过渡操作员的线性谱特征。基于该观察,我们提出了嵌入(Spede)的谱动力学嵌入(SPEDE),这将通过利用噪声结构来完成对代表学习的乐观探索。我们提供对Speded的严格理论分析,并展示了几种基准上现有最先进的实证算法的实际卓越性能。
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
强大的增强学习(RL)的目的是学习一项与模型参数不确定性的强大策略。由于模拟器建模错误,随着时间的推移,现实世界系统动力学的变化以及对抗性干扰,参数不确定性通常发生在许多现实世界中的RL应用中。强大的RL通常被称为最大问题问题,其目的是学习最大化价值与不确定性集合中最坏可能的模型的策略。在这项工作中,我们提出了一种称为鲁棒拟合Q-材料(RFQI)的强大RL算法,该算法仅使用离线数据集来学习最佳稳健策略。使用离线数据的强大RL比其非持续性对应物更具挑战性,因为在强大的Bellman运营商中所有模型的最小化。这在离线数据收集,对模型的优化以及公正的估计中构成了挑战。在这项工作中,我们提出了一种系统的方法来克服这些挑战,从而导致了我们的RFQI算法。我们证明,RFQI在标准假设下学习了一项近乎最佳的强大政策,并证明了其在标准基准问题上的出色表现。
translated by 谷歌翻译
平衡勘探和剥削对加强学习(RL)至关重要。在本文中,我们在理论上和经验上,研究了用于连续状态行动空间的加固学习(PSRL)的模型后采样。首先,我们在连续空间中显示PSRL的第一个遗憾,这是我们知识中的最佳地段中的多项式。假设奖励和转换函数可以由贝叶斯线性回归建模,我们开发了$ \ tilde {o}的遗憾(h ^ {3/2} d \ sqrt {t})$,其中$ h $剧集长度,$ D $是状态动作空间的维度,$ t $表示总时间步骤。此结果与线性MDP中的非PSRL方法的最佳已知的遗憾符合。我们的绑定可以扩展到非线性情况以及功能嵌入功能:在特征表示上的线性内核$ \ phi $,后悔绑定成为$ \ tilde {o}(h ^ {3/2} d _ {\ phi} \ SQRT {T})$,其中$ d_ \ phi $是表示空间的尺寸。此外,我们呈现MPC-PSRL,一种基于模型的后部采样算法,具有用于动作选择的模型预测控制。为了捕获模型中的不确定性,我们在神经网络的倒数第二层(特征表示层$ \ phi $)上使用贝叶斯线性回归。实证结果表明,与基于模型的算法相比,我们的算法在基准连续控制任务中实现了最先进的示例效率,并匹配无模型算法的渐近性能。
translated by 谷歌翻译
Model-free deep reinforcement learning (RL) algorithms have been demonstrated on a range of challenging decision making and control tasks. However, these methods typically suffer from two major challenges: very high sample complexity and brittle convergence properties, which necessitate meticulous hyperparameter tuning. Both of these challenges severely limit the applicability of such methods to complex, real-world domains. In this paper, we propose soft actor-critic, an offpolicy actor-critic deep RL algorithm based on the maximum entropy reinforcement learning framework. In this framework, the actor aims to maximize expected reward while also maximizing entropy. That is, to succeed at the task while acting as randomly as possible. Prior deep RL methods based on this framework have been formulated as Q-learning methods. By combining off-policy updates with a stable stochastic actor-critic formulation, our method achieves state-of-the-art performance on a range of continuous control benchmark tasks, outperforming prior on-policy and off-policy methods. Furthermore, we demonstrate that, in contrast to other off-policy algorithms, our approach is very stable, achieving very similar performance across different random seeds.
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
Pessimism is of great importance in offline reinforcement learning (RL). One broad category of offline RL algorithms fulfills pessimism by explicit or implicit behavior regularization. However, most of them only consider policy divergence as behavior regularization, ignoring the effect of how the offline state distribution differs with that of the learning policy, which may lead to under-pessimism for some states and over-pessimism for others. Taking account of this problem, we propose a principled algorithmic framework for offline RL, called \emph{State-Aware Proximal Pessimism} (SA-PP). The key idea of SA-PP is leveraging discounted stationary state distribution ratios between the learning policy and the offline dataset to modulate the degree of behavior regularization in a state-wise manner, so that pessimism can be implemented in a more appropriate way. We first provide theoretical justifications on the superiority of SA-PP over previous algorithms, demonstrating that SA-PP produces a lower suboptimality upper bound in a broad range of settings. Furthermore, we propose a new algorithm named \emph{State-Aware Conservative Q-Learning} (SA-CQL), by building SA-PP upon representative CQL algorithm with the help of DualDICE for estimating discounted stationary state distribution ratios. Extensive experiments on standard offline RL benchmark show that SA-CQL outperforms the popular baselines on a large portion of benchmarks and attains the highest average return.
translated by 谷歌翻译
安全政策改进(SPI)是在安全关键应用中脱机加强学习的重要技术,因为它以很高的可能性改善了行为政策。我们根据如何利用国家行动对的不确定性将各种SPI方法分为两组。为了关注软SPIBB(通过软基线自举的安全政策改进)算法,我们表明他们对被证明安全的主张不坚持。基于这一发现,我们开发了适应性,Adv-Soft SpibB算法,并证明它们是可以安全的。在两个基准上进行的广泛实验中,启发式适应性较低的SPOBB在所有SPIBB算法中都能表现出最佳性能。我们还检查了可证明的安全算法的安全保证,并表明有大量数据是必要的,以使安全界限在实践中变得有用。
translated by 谷歌翻译
无模型的深度增强学习(RL)已成功应用于挑战连续控制域。然而,较差的样品效率可防止这些方法广泛用于现实世界领域。我们通过提出一种新的无模型算法,现实演员 - 评论家(RAC)来解决这个问题,旨在通过学习关于Q函数的各种信任的政策家庭来解决价值低估和高估之间的权衡。我们构建不确定性惩罚Q-Learning(UPQ),该Q-Learning(UPQ)使用多个批评者的合并来控制Q函数的估计偏差,使Q函数平稳地从低于更高的置信范围偏移。随着这些批评者的指导,RAC采用通用价值函数近似器(UVFA),同时使用相同的神经网络学习许多乐观和悲观的政策。乐观的政策会产生有效的探索行为,而悲观政策会降低价值高估的风险,以确保稳定的策略更新和Q函数。该方法可以包含任何违规的演员 - 评论家RL算法。我们的方法实现了10倍的样本效率和25 \%的性能改进与SAC在最具挑战性的人形环境中,获得了11107美元的集中奖励1107美元,价格为10 ^ 6美元。所有源代码都可以在https://github.com/ihuhuhu/rac获得。
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
在不确定性面前的乐观原则在整个连续决策中普遍存在,如多武装匪和加强学习(RL)等问题。为了成功,乐观的RL算法必须过度估计真正的值函数(乐观),但不是通过它不准确的(估计错误)。在表格设置中,许多最先进的方法通过在缩放到深rl时难以应变的方法产生所需的乐观。我们重新解释基于可扩展的乐观模型的算法,以解决易解噪声增强MDP。这种配方实现了竞争遗憾:$ \ tilde {\ mathcal {o}}(| \ mathcal {s} | h \ sqrt {| \ mathcal {a} | t} $在使用高斯噪音时,$ t $是环境步骤的总数。我们还探讨了这种权衡在深度RL设置中的权衡变化,我们在验证上显示估计误差明显更麻烦。但是,我们还表明,如果此错误减少,基于乐观的模型的RL算法可以在连续控制问题中匹配最先进的性能。
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