在本文中,我们提出了一种新颖的重尾随机策略梯度(HT-PSG)算法,以应对连续控制问题中稀疏奖励的挑战。稀疏的奖励在连续控制机器人技术任务(例如操纵和导航)中很常见,并且由于对状态空间的价值功能的非平凡估计而使学习问题变得困难。这需要奖励成型或针对稀疏奖励环境的专家演示。但是,获得高质量的演示非常昂贵,有时甚至是不可能的。我们提出了一个重型策略参数化,以及基于动量的策略梯度跟踪方案(HT-SPG),以引起对算法的稳定探索行为。提出的算法不需要访问专家演示。我们测试了HT-SPG在连续控制的各种基准测试任务上的性能,并具有稀疏的奖励,例如1d Mario,病理山车,Openai体育馆的稀疏摆和稀疏的Mujoco环境(Hopper-V2)。就高平均累积奖励而言,我们在所有任务中表现出一致的性能提高。 HT-SPG还证明了最低样品的收敛速度提高,从而强调了我们提出的算法的样品效率。
translated by 谷歌翻译
我们提出了一种新的方法,以改善基于深入强化学习(DRL)的室外机器人导航系统的性能。大多数现有的DRL方法基于精心设计的密集奖励功能,这些功能可以学习环境中的有效行为。我们仅通过稀疏的奖励(易于设计)来解决这个问题,并提出了一种新颖的自适应重尾增强算法,用于户外导航,称为Htron。我们的主要思想是利用重尾政策参数化,这些参数隐含在稀疏的奖励环境中引起探索。我们在三种不同的室外场景中评估了针对钢琴,PPO和TRPO算法的htron的性能:进球,避免障碍和地形导航不均匀。我们平均观察到成功率的平均增加了34.41%,与其他方法相比,与其他方法获得的导航政策相比,为达到目标的平均时间步骤下降了15.15%,高程成本下降了24.9%。此外,我们证明我们的算法可以直接转移到Clearpath Husky机器人中,以在现实情况下进行户外地形导航。
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
元加强学习(META-RL)是一种方法,即从解决各种任务中获得的经验被蒸馏成元政策。当仅适应一个小(或仅一个)数量的步骤时,元派利赛能够在新的相关任务上近距离执行。但是,采用这种方法来解决现实世界中的问题的主要挑战是,它们通常与稀疏的奖励功能相关联,这些功能仅表示任务是部分或完全完成的。我们考虑到某些数据可能由亚最佳代理生成的情况,可用于每个任务。然后,我们使用示范(EMRLD)开发了一类名为“增强元RL”的算法,即使在训练过程中获得了次优的指导,也可以利用此信息。我们展示了EMRLD如何共同利用RL和在离线数据上进行监督学习,以生成一个显示单调性能改进的元数据。我们还开发了一个称为EMRLD-WS的温暖开始的变体,该变体对于亚最佳演示数据特别有效。最后,我们表明,在包括移动机器人在内的各种稀疏奖励环境中,我们的EMRLD算法显着优于现有方法。
translated by 谷歌翻译
With the development of deep representation learning, the domain of reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. This review summarises deep reinforcement learning (DRL) algorithms and provides a taxonomy of automated driving tasks where (D)RL methods have been employed, while addressing key computational challenges in real world deployment of autonomous driving agents. It also delineates adjacent domains such as behavior cloning, imitation learning, inverse reinforcement learning that are related but are not classical RL algorithms. The role of simulators in training agents, methods to validate, test and robustify existing solutions in RL are discussed.
translated by 谷歌翻译
Deep Reinforcement Learning has been successfully applied to learn robotic control. However, the corresponding algorithms struggle when applied to problems where the agent is only rewarded after achieving a complex task. In this context, using demonstrations can significantly speed up the learning process, but demonstrations can be costly to acquire. In this paper, we propose to leverage a sequential bias to learn control policies for complex robotic tasks using a single demonstration. To do so, our method learns a goal-conditioned policy to control a system between successive low-dimensional goals. This sequential goal-reaching approach raises a problem of compatibility between successive goals: we need to ensure that the state resulting from reaching a goal is compatible with the achievement of the following goals. To tackle this problem, we present a new algorithm called DCIL-II. We show that DCIL-II can solve with unprecedented sample efficiency some challenging simulated tasks such as humanoid locomotion and stand-up as well as fast running with a simulated Cassie robot. Our method leveraging sequentiality is a step towards the resolution of complex robotic tasks under minimal specification effort, a key feature for the next generation of autonomous robots.
translated by 谷歌翻译
降低策略梯度方法方差的梯度估计器已成为近年来增强学习研究的主要重点之一,因为它们允许加速估算过程。我们提出了一种称为Sharp的方差降低的策略梯度方法,该方法将二阶信息纳入随机梯度下降(SGD)中,并使用动量和时间变化的学习率。 Sharp Algorithm无参数,实现$ \ Epsilon $ - Appro-Appro-Approximate固定点,带有$ O(\ Epsilon^{ - 3})$的轨迹数,同时使用批量的大小为$ O(1)$迭代。与以前的大多数工作不同,我们提出的算法不需要重要的抽样,这可能会损害降低方差的优势。此外,估计错误的差异会以$ o(1/t^{2/3})$的快速速率衰减,其中$ t $是迭代的数量。我们广泛的实验评估表明,拟议算法对各种控制任务的有效性及其对实践中最新状态的优势。
translated by 谷歌翻译
如何在演示相对较大时更加普遍地进行模仿学习一直是强化学习(RL)的持续存在问题。糟糕的示威活动导致狭窄和偏见的日期分布,非马洛维亚人类专家演示使代理商难以学习,而过度依赖子最优轨迹可以使代理商努力提高其性能。为了解决这些问题,我们提出了一种名为TD3FG的新算法,可以平稳地过渡从专家到学习从经验中学习。我们的算法在Mujoco环境中实现了有限的有限和次优的演示。我们使用行为克隆来将网络作为参考动作发生器训练,并在丢失函数和勘探噪声方面使用它。这种创新可以帮助代理商从示威活动中提取先验知识,同时降低了糟糕的马尔科维亚特性的公正的不利影响。与BC +微调和DDPGFD方法相比,它具有更好的性能,特别是当示范相对有限时。我们调用我们的方法TD3FG意味着来自发电机的TD3。
translated by 谷歌翻译
通过加强学习(RL)掌握机器人操纵技巧通常需要设计奖励功能。该地区的最新进展表明,使用稀疏奖励,即仅在成功完成任务时奖励代理,可能会导致更好的政策。但是,在这种情况下,国家行动空间探索更困难。最近的RL与稀疏奖励学习的方法已经为任务提供了高质量的人类演示,但这些可能是昂贵的,耗时甚至不可能获得的。在本文中,我们提出了一种不需要人类示范的新颖有效方法。我们观察到,每个机器人操纵任务都可以被视为涉及从被操纵对象的角度来看运动的任务,即,对象可以了解如何自己达到目标状态。为了利用这个想法,我们介绍了一个框架,最初使用现实物理模拟器获得对象运动策略。然后,此策略用于生成辅助奖励,称为模拟的机器人演示奖励(SLDRS),使我们能够学习机器人操纵策略。拟议的方法已在增加复杂性的13个任务中进行了评估,与替代算法相比,可以实现更高的成功率和更快的学习率。 SLDRS对多对象堆叠和非刚性物体操作等任务特别有益。
translated by 谷歌翻译
仿制学习(IL)是在连续控制环境中的流行方法,如其他原因,它避免了加固学习中奖励错误规范和探索的问题(RL)。在IL的示威中,一个重要的挑战是获得对投入顺利进行的代理政策。通过模仿作为一个稳定的函数来学习,这是一种顺利的策略($ S $-$)空间(典型的高维连续控制环境)可能是具有挑战性的。我们采取了第一步迈出了通过使用\ Texit {两者}的策略和成本模型来解决这个问题的解决这个问题。我们的符合方案通过确保成本函数以受控方式变化为$ S $的函数 - $空间;而代理政策对国家空间良好表现得很好。我们称之为新的顺利IL算法\«Spoolly Policy和Cost Imitation Learning}(Spacil,Pronoughce'Special')。我们介绍了一种新的指标来量化学习政策的顺利。我们展示了Spacil在Mujoco的连续控制任务方面的卓越性能。该算法不仅优于我们所提出的平滑度指标的最先进的IL算法,但是,享有更快的学习和大幅更高的平均回报的增加的好处。
translated by 谷歌翻译
仿制学习(IL)是一个框架,了解从示范中模仿专家行为。最近,IL显示了高维和控制任务的有希望的结果。然而,IL通常遭受环境互动方面的样本低效率,这严重限制了它们对模拟域的应用。在工业应用中,学习者通常具有高的相互作用成本,与环境的互动越多,对环境的损害越多,学习者本身就越多。在本文中,我们努力通过引入逆钢筋学习的新颖方案来提高样本效率。我们的方法,我们调用\ texit {model redion函数基础的模仿学习}(mrfil),使用一个集合动态模型作为奖励功能,是通过专家演示培训的内容。关键的想法是通过在符合专家示范分布时提供积极奖励,为代理商提供与漫长地平线相匹配的演示。此外,我们展示了新客观函数的收敛保证。实验结果表明,与IL方法相比,我们的算法达到了竞争性能,并显着降低了环境交互。
translated by 谷歌翻译
Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually shaping a reward function can result in suboptimal performance. However, finding a non-zero reward is exponentially more difficult with increasing task horizon or action dimensionality. This puts many real-world tasks out of practical reach of RL methods. In this work, we use demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous control such as stacking blocks with a robot arm. Our method, which builds on top of Deep Deterministic Policy Gradients and Hindsight Experience Replay, provides an order of magnitude of speedup over RL on simulated robotics tasks. It is simple to implement and makes only the additional assumption that we can collect a small set of demonstrations. Furthermore, our method is able to solve tasks not solvable by either RL or behavior cloning alone, and often ends up outperforming the demonstrator policy.
translated by 谷歌翻译
深度强化学习(DRL)和深度多机构的强化学习(MARL)在包括游戏AI,自动驾驶汽车,机器人技术等各种领域取得了巨大的成功。但是,众所周知,DRL和Deep MARL代理的样本效率低下,即使对于相对简单的问题设置,通常也需要数百万个相互作用,从而阻止了在实地场景中的广泛应用和部署。背后的一个瓶颈挑战是众所周知的探索问题,即如何有效地探索环境和收集信息丰富的经验,从而使政策学习受益于最佳研究。在稀疏的奖励,吵闹的干扰,长距离和非平稳的共同学习者的复杂环境中,这个问题变得更加具有挑战性。在本文中,我们对单格和多代理RL的现有勘探方法进行了全面的调查。我们通过确定有效探索的几个关键挑战开始调查。除了上述两个主要分支外,我们还包括其他具有不同思想和技术的著名探索方法。除了算法分析外,我们还对一组常用基准的DRL进行了全面和统一的经验比较。根据我们的算法和实证研究,我们终于总结了DRL和Deep Marl中探索的公开问题,并指出了一些未来的方向。
translated by 谷歌翻译
本文考虑了从专家演示中学习机器人运动和操纵任务。生成对抗性模仿学习(GAIL)训练一个区分专家与代理转换区分开的歧视者,进而使用歧视器输出定义的奖励来优化代理商的策略生成器。这种生成的对抗训练方法非常强大,但取决于歧视者和发电机培训之间的微妙平衡。在高维问题中,歧视训练可能很容易过度拟合或利用与任务 - 核定功能进行过渡分类的关联。这项工作的一个关键见解是,在合适的潜在任务空间中进行模仿学习使训练过程稳定,即使在挑战高维问题中也是如此。我们使用动作编码器模型来获得低维的潜在动作空间,并使用对抗性模仿学习(Lapal)训练潜在政策。可以从州行动对脱机来训练编码器模型,以获得任务无关的潜在动作表示或与歧视器和发电机培训同时在线获得,以获得任务意识到的潜在行动表示。我们证明了Lapal训练是稳定的,具有近乎单的性能的改进,并在大多数运动和操纵任务中实现了专家性能,而Gail基线收敛速度较慢,并且在高维环境中无法实现专家的表现。
translated by 谷歌翻译
仿制学习(IL)是一种有效的学习范例,利用代理和环境之间的交互。它不需要显式奖励信号,而是尝试使用专家演示恢复所需的策略。通常,IL方法可以分类为行为克隆(BC)和逆钢筋学习(IRL)。在这项工作中,提出了一种基于概率密度估计的新型奖励功能,用于IRL,这可以显着降低现有IRL方法的复杂性。此外,我们证明,只要确定性,我们源自奖励函数的理论上最佳政策与专家政策相同。因此,可以优雅地将IRL问题变为概率密度估计问题。基于所提出的奖励函数,我们展示了一个“观看 - 尝试学习”样式框架命名概率密度估计的基于仿真学习(PDEIL),其可以在离散和连续的动作空间中工作。最后,在健身房环境中的综合实验表明,Pdeil比现有算法恢复靠近地面真理的奖励更有效。
translated by 谷歌翻译
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
Adequately assigning credit to actions for future outcomes based on their contributions is a long-standing open challenge in Reinforcement Learning. The assumptions of the most commonly used credit assignment method are disadvantageous in tasks where the effects of decisions are not immediately evident. Furthermore, this method can only evaluate actions that have been selected by the agent, making it highly inefficient. Still, no alternative methods have been widely adopted in the field. Hindsight Credit Assignment is a promising, but still unexplored candidate, which aims to solve the problems of both long-term and counterfactual credit assignment. In this thesis, we empirically investigate Hindsight Credit Assignment to identify its main benefits, and key points to improve. Then, we apply it to factored state representations, and in particular to state representations based on the causal structure of the environment. In this setting, we propose a variant of Hindsight Credit Assignment that effectively exploits a given causal structure. We show that our modification greatly decreases the workload of Hindsight Credit Assignment, making it more efficient and enabling it to outperform the baseline credit assignment method on various tasks. This opens the way to other methods based on given or learned causal structures.
translated by 谷歌翻译
Safe Reinforcement Learning can be defined as the process of learning policies that maximize the expectation of the return in problems in which it is important to ensure reasonable system performance and/or respect safety constraints during the learning and/or deployment processes. We categorize and analyze two approaches of Safe Reinforcement Learning. The first is based on the modification of the optimality criterion, the classic discounted finite/infinite horizon, with a safety factor. The second is based on the modification of the exploration process through the incorporation of external knowledge or the guidance of a risk metric. We use the proposed classification to survey the existing literature, as well as suggesting future directions for Safe Reinforcement Learning.
translated by 谷歌翻译
强化学习和最近的深度增强学习是解决如Markov决策过程建模的顺序决策问题的流行方法。问题和选择算法和超参数的RL建模需要仔细考虑,因为不同的配置可能需要完全不同的性能。这些考虑因素主要是RL专家的任务;然而,RL在研究人员和系统设计师不是RL专家的其他领域中逐渐变得流行。此外,许多建模决策,例如定义状态和动作空间,批次的大小和批量更新的频率以及时间戳的数量通常是手动进行的。由于这些原因,RL框架的自动化不同组成部分具有重要意义,近年来它引起了很多关注。自动RL提供了一个框架,其中RL的不同组件包括MDP建模,算法选择和超参数优化是自动建模和定义的。在本文中,我们探讨了可以在自动化RL中使用的文献和目前的工作。此外,我们讨论了Autorl中的挑战,打开问题和研究方向。
translated by 谷歌翻译
Deep reinforcement learning is poised to revolutionise the field of AI and represents a step towards building autonomous systems with a higher level understanding of the visual world. Currently, deep learning is enabling reinforcement learning to scale to problems that were previously intractable, such as learning to play video games directly from pixels. Deep reinforcement learning algorithms are also applied to robotics, allowing control policies for robots to be learned directly from camera inputs in the real world. In this survey, we begin with an introduction to the general field of reinforcement learning, then progress to the main streams of value-based and policybased methods. Our survey will cover central algorithms in deep reinforcement learning, including the deep Q-network, trust region policy optimisation, and asynchronous advantage actor-critic. In parallel, we highlight the unique advantages of deep neural networks, focusing on visual understanding via reinforcement learning. To conclude, we describe several current areas of research within the field.
translated by 谷歌翻译