离线强化学习(RL)任务要求代理从预先收集的数据集中学习,没有与环境进行进一步的交互。尽管有可能超越行为政策,但基于RL的方法通常是不切实际的,因为培训不稳定并引导外推错误,这始终需要通过在线评估进行仔细的超参数调整。相比之下,离线模仿学习(IL)没有这样的问题,因为它直接在不估计值函数的情况下直接了解策略。然而,IL通常限制在行为政策的能力,并且倾向于从政策混合收集的数据集中学习平庸行为。在本文中,我们的目标是利用IL但缓解这种缺点。观察行为克隆能够使用较少的数据模仿邻近的策略,我们提出\ Textit {课程脱机仿制学习(线圈)},它利用具有更高回报的自适应邻近策略的体验挑选策略,并提高了当前策略沿课程阶段。在连续控制基准测试中,我们将线圈与基于仿制的和基于RL的方法进行比较,表明它不仅避免了在混合数据集上学习平庸行为,而且甚至与最先进的离线RL方法竞争。
translated by 谷歌翻译
我们研究了离线模仿学习(IL)的问题,在该问题中,代理商旨在学习最佳的专家行为政策,而无需其他在线环境互动。取而代之的是,该代理来自次优行为的补充离线数据集。解决此问题的先前工作要么要求专家数据占据离线数据集的大部分比例,要么需要学习奖励功能并在以后执行离线加强学习(RL)。在本文中,我们旨在解决问题,而无需进行奖励学习和离线RL培训的其他步骤,当时示范包含大量次优数据。基于行为克隆(BC),我们引入了一个额外的歧视者,以区分专家和非专家数据。我们提出了一个合作框架,以增强这两个任务的学习,基于此框架,我们设计了一种新的IL算法,其中歧视者的输出是BC损失的权重。实验结果表明,与基线算法相比,我们提出的算法可获得更高的回报和更快的训练速度。
translated by 谷歌翻译
仅国家模仿学习的最新进展将模仿学习的适用性扩展到现实世界中的范围,从而减轻了观察专家行动的需求。但是,现有的解决方案只学会从数据中提取州对行动映射策略,而无需考虑专家如何计划到目标。这阻碍了利用示威游行并限制政策的灵活性的能力。在本文中,我们介绍了解耦政策优化(DEPO),该策略优化(DEPO)明确将策略脱离为高级状态计划者和逆动力学模型。借助嵌入式的脱钩策略梯度和生成对抗训练,DEPO可以将知识转移到不同的动作空间或状态过渡动态,并可以将规划师推广到无示威的状态区域。我们的深入实验分析表明,DEPO在学习最佳模仿性能的同时学习通用目标状态计划者的有效性。我们证明了DEPO通过预训练跨任务转移的吸引力,以及与各种技能共同培训的潜力。
translated by 谷歌翻译
离线增强学习(RL)定义了从静态记录数据集学习的任务,而无需与环境不断交互。学识渊博的政策与行为政策之间的分配变化使得价值函数必须保持保守,以使分布(OOD)的动作不会被严重高估。但是,现有的方法,对看不见的行为进行惩罚或与行为政策进行正规化,太悲观了,这抑制了价值功能的概括并阻碍了性能的提高。本文探讨了温和但足够的保守主义,可以在线学习,同时不损害概括。我们提出了轻度保守的Q学习(MCQ),其中通过分配了适当的伪Q值来积极训练OOD。从理论上讲,我们表明MCQ诱导了至少与行为策略的行为,并且对OOD行动不会发生错误的高估。 D4RL基准测试的实验结果表明,与先前的工作相比,MCQ取得了出色的性能。此外,MCQ在从离线转移到在线时显示出卓越的概括能力,并明显胜过基准。
translated by 谷歌翻译
我们提出了状态匹配的离线分布校正估计(SMODICE),这是一种新颖且基于多功能回归的离线模仿学习(IL)算法,该算法是通过状态占用匹配得出的。我们表明,SMODICE目标通过在表格MDP中的Fenchel二元性和一个分析解决方案的应用来接受一个简单的优化过程。不需要访问专家的行动,可以将Smodice有效地应用于三个离线IL设置:(i)模仿观察值(IFO),(ii)IFO具有动态或形态上不匹配的专家,以及(iii)基于示例的加固学习,这些学习我们表明可以将其公式为州占领的匹配问题。我们在GridWorld环境以及高维离线基准上广泛评估了Smodice。我们的结果表明,Smodice对于所有三个问题设置都有效,并且在前最新情况下均明显胜过。
translated by 谷歌翻译
在许多顺序决策问题(例如,机器人控制,游戏播放,顺序预测),人类或专家数据可用包含有关任务的有用信息。然而,来自少量专家数据的模仿学习(IL)可能在具有复杂动态的高维环境中具有挑战性。行为克隆是一种简单的方法,由于其简单的实现和稳定的收敛而被广泛使用,但不利用涉及环境动态的任何信息。由于对奖励和政策近似器或偏差,高方差梯度估计器,难以在实践中难以在实践中努力训练的许多现有方法。我们介绍了一种用于动态感知IL的方法,它通过学习单个Q函数来避免对抗训练,隐含地代表奖励和策略。在标准基准测试中,隐式学习的奖励显示与地面真实奖励的高正面相关性,说明我们的方法也可以用于逆钢筋学习(IRL)。我们的方法,逆软Q学习(IQ-Learn)获得了最先进的结果,在离线和在线模仿学习设置中,显着优于现有的现有方法,这些方法都在所需的环境交互和高维空间中的可扩展性中,通常超过3倍。
translated by 谷歌翻译
Deep reinforcement learning (DRL) provides a new way to generate robot control policy. However, the process of training control policy requires lengthy exploration, resulting in a low sample efficiency of reinforcement learning (RL) in real-world tasks. Both imitation learning (IL) and learning from demonstrations (LfD) improve the training process by using expert demonstrations, but imperfect expert demonstrations can mislead policy improvement. Offline to Online reinforcement learning requires a lot of offline data to initialize the policy, and distribution shift can easily lead to performance degradation during online fine-tuning. To solve the above problems, we propose a learning from demonstrations method named A-SILfD, which treats expert demonstrations as the agent's successful experiences and uses experiences to constrain policy improvement. Furthermore, we prevent performance degradation due to large estimation errors in the Q-function by the ensemble Q-functions. Our experiments show that A-SILfD can significantly improve sample efficiency using a small number of different quality expert demonstrations. In four Mujoco continuous control tasks, A-SILfD can significantly outperform baseline methods after 150,000 steps of online training and is not misled by imperfect expert demonstrations during training.
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
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
在离线强化学习(离线RL)中,主要挑战之一是处理学习策略与给定数据集之间的分布转变。为了解决这个问题,最近的离线RL方法试图引入保守主义偏见,以鼓励在高信心地区学习。无模型方法使用保守的正常化或特殊网络结构直接对策略或价值函数学习进行这样的偏见,但它们约束的策略搜索限制了脱机数据集之外的泛化。基于模型的方法使用保守量量化学习前瞻性动态模型,然后生成虚构的轨迹以扩展脱机数据集。然而,由于离线数据集中的有限样本,保守率量化通常在支撑区域内遭受全面化。不可靠的保守措施将误导基于模型的想象力,以不受欢迎的地区,导致过多的行为。为了鼓励更多的保守主义,我们提出了一种基于模型的离线RL框架,称为反向离线模型的想象(ROMI)。我们与新颖的反向策略结合使用逆向动力学模型,该模型可以生成导致脱机数据集中的目标目标状态的卷展栏。这些反向的想象力提供了无通知的数据增强,以便无模型策略学习,并使远程数据集的保守概括。 ROMI可以有效地与现成的无模型算法组合,以实现基于模型的概括,具有适当的保守主义。经验结果表明,我们的方法可以在离线RL基准任务中产生更保守的行为并实现最先进的性能。
translated by 谷歌翻译
Behavioural cloning (BC) is a commonly used imitation learning method to infer a sequential decision-making policy from expert demonstrations. However, when the quality of the data is not optimal, the resulting behavioural policy also performs sub-optimally once deployed. Recently, there has been a surge in offline reinforcement learning methods that hold the promise to extract high-quality policies from sub-optimal historical data. A common approach is to perform regularisation during training, encouraging updates during policy evaluation and/or policy improvement to stay close to the underlying data. In this work, we investigate whether an offline approach to improving the quality of the existing data can lead to improved behavioural policies without any changes in the BC algorithm. The proposed data improvement approach - Trajectory Stitching (TS) - generates new trajectories (sequences of states and actions) by `stitching' pairs of states that were disconnected in the original data and generating their connecting new action. By construction, these new transitions are guaranteed to be highly plausible according to probabilistic models of the environment, and to improve a state-value function. We demonstrate that the iterative process of replacing old trajectories with new ones incrementally improves the underlying behavioural policy. Extensive experimental results show that significant performance gains can be achieved using TS over BC policies extracted from the original data. Furthermore, using the D4RL benchmarking suite, we demonstrate that state-of-the-art results are obtained by combining TS with two existing offline learning methodologies reliant on BC, model-based offline planning (MBOP) and policy constraint (TD3+BC).
translated by 谷歌翻译
Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and actor-critic methods are highly sensitive to the data distribution, and can make only limited progress without collecting additional on-policy data. As a step towards more robust off-policy algorithms, we study the setting where the off-policy experience is fixed and there is no further interaction with the environment. We identify bootstrapping error as a key source of instability in current methods. Bootstrapping error is due to bootstrapping from actions that lie outside of the training data distribution, and it accumulates via the Bellman backup operator. We theoretically analyze bootstrapping error, and demonstrate how carefully constraining action selection in the backup can mitigate it. Based on our analysis, we propose a practical algorithm, bootstrapping error accumulation reduction (BEAR). We demonstrate that BEAR is able to learn robustly from different off-policy distributions, including random and suboptimal demonstrations, on a range of continuous control tasks.
translated by 谷歌翻译
Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to errors introduced by extrapolation, standard offpolicy deep reinforcement learning algorithms, such as DQN and DDPG, are incapable of learning without data correlated to the distribution under the current policy, making them ineffective for this fixed batch setting. We introduce a novel class of off-policy algorithms, batch-constrained reinforcement learning, which restricts the action space in order to force the agent towards behaving close to on-policy with respect to a subset of the given data. We present the first continuous control deep reinforcement learning algorithm which can learn effectively from arbitrary, fixed batch data, and empirically demonstrate the quality of its behavior in several tasks.
translated by 谷歌翻译
我们提供了一种通过从域知识或离线数据构建的启发式提供加强学习(RL)算法的框架。 Tabula RAS RL算法需要与顺序决策任务的地平线相比的环境相互作用或计算。使用我们的框架,我们展示了启发式引导的RL如何引导更短的地平次数,可从而解决原始任务。我们的框架可以被视为基于地平线的正则化,用于在有限互动预算下控制RL中的偏差和方差。在理论方面,我们表征了良好启发式的特性及其对RL加速的影响。特别是,我们介绍了一种新颖的启发式的概念,一种启发式,允许RL代理外推超出其先前知识。在实证方面,我们实例化了我们的框架,以加速模拟机器人控制任务和程序生成的游戏中的若干最先进的算法。我们的框架在热启动RL与专家演示或探索数据集中的丰富文学补充,并引入了一种用于将先验知识注入RL的原则方法。
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
模仿学习从专家轨迹中学习政策。尽管据信专家数据对于模仿质量至关重要,但发现一种模仿学习方法,对抗性模仿学习(AIL)可以具有出色的性能。只需仅仅在一个专家轨迹上,即使在诸如运动控制之类的任务上,AIL也可以符合专家的性能。这种现象有两个神秘的要点。首先,为什么AIL只能使用几个专家轨迹表现良好?其次,尽管计划范围的时间长,但为什么AIL仍能保持良好的性能?在本文中,我们从理论上探讨了这两个问题。对于总基于差异的ail(称为TV-ail),我们的分析显示了一个无水平的模仿差距$ \ MATHCAL O(\ {\ {\ min \ {1,\ sqrt {| \ Mathcal S |/n} \})$在从运动控制任务中抽象的一类实例上。这里$ | \ Mathcal S | $是表格Markov决策过程的状态空间大小,而$ n $是专家轨迹的数量。我们强调了界限的两个重要特征。首先,在小样本制度中,这种界限都是有意义的。其次,这一界限表明,无论计划范围如何,电视填充的模仿缝隙最多都是1。因此,这种结合可以解释经验观察。从技术上讲,我们利用了电视填充中多阶段策略优化的结构,并通过动态编程提出了新的舞台耦合分析
translated by 谷歌翻译
仿制学习(IL)是一个框架,了解从示范中模仿专家行为。最近,IL显示了高维和控制任务的有希望的结果。然而,IL通常遭受环境互动方面的样本低效率,这严重限制了它们对模拟域的应用。在工业应用中,学习者通常具有高的相互作用成本,与环境的互动越多,对环境的损害越多,学习者本身就越多。在本文中,我们努力通过引入逆钢筋学习的新颖方案来提高样本效率。我们的方法,我们调用\ texit {model redion函数基础的模仿学习}(mrfil),使用一个集合动态模型作为奖励功能,是通过专家演示培训的内容。关键的想法是通过在符合专家示范分布时提供积极奖励,为代理商提供与漫长地平线相匹配的演示。此外,我们展示了新客观函数的收敛保证。实验结果表明,与IL方法相比,我们的算法达到了竞争性能,并显着降低了环境交互。
translated by 谷歌翻译
在现实世界中,通过弱势政策影响环境可能是昂贵的或非常危险的,因此妨碍了现实世界的加强学习应用。离线强化学习(RL)可以从给定数据集中学习策略,而不与环境进行交互。但是,数据集是脱机RL算法的唯一信息源,并确定学习策略的性能。我们仍然缺乏关于数据集特征如何影响不同离线RL算法的研究。因此,我们对数据集特性如何实现离散动作环境的离线RL算法的性能的全面实证分析。数据集的特点是两个度量:(1)通过轨迹质量(TQ)测量的平均数据集返回和(2)由状态 - 动作覆盖(SACO)测量的覆盖范围。我们发现,禁止政策深度Q网家族的变体需要具有高SACO的数据集来表现良好。将学习策略朝向给定数据集的算法对具有高TQ或SACO的数据集进行了良好。对于具有高TQ的数据集,行为克隆优先级或类似于最好的离线RL算法。
translated by 谷歌翻译
离线强化学习在利用大型预采用的数据集进行政策学习方面表现出了巨大的希望,使代理商可以放弃经常廉价的在线数据收集。但是,迄今为止,离线强化学习的探索相对较小,并且缺乏对剩余挑战所在的何处的了解。在本文中,我们试图建立简单的基线以在视觉域中连续控制。我们表明,对两个基于最先进的在线增强学习算法,Dreamerv2和DRQ-V2进行了简单的修改,足以超越事先工作并建立竞争性的基准。我们在现有的离线数据集中对这些算法进行了严格的评估,以及从视觉观察结果中进行离线强化学习的新测试台,更好地代表现实世界中离线增强学习问题中存在的数据分布,并开放我们的代码和数据以促进此方面的进度重要领域。最后,我们介绍并分析了来自视觉观察的离线RL所独有的几个关键Desiderata,包括视觉分散注意力和动态视觉上可识别的变化。
translated by 谷歌翻译
在线模仿学习是如何最好地访问环境或准确的模拟器的问题的问题。先前的工作表明,在无限的样本制度中,匹配的确切力矩达到了与专家政策的价值等效性。但是,在有限的样本制度中,即使没有优化错误,经验差异也会导致性能差距,该差距以$ h^2 / n $的行为克隆缩放,在线时刻$ h / \ sqrt {n} $匹配,其中$ h $是地平线,$ n $是专家数据集的大小。我们介绍了重播估算的技术以减少这种经验差异:通过反复在随机模拟器中执行缓存的专家动作,我们计算了一个更平滑的专家访问分布估算以匹配的。在存在一般函数近似的情况下,我们证明了一个元定理,可以减少离线分类参数估计误差的方法差距(即学习专家策略)。在表格设置或使用线性函数近似中,我们的元定理表明,我们方法产生的性能差距达到了最佳$ \ widetilde {o} \ left(\ min(\ min({h^h^{3/2}}}} / {n} ,{h} / {\ sqrt {n}} \ right)$依赖关系,在与先前的工作相比明显弱的假设下。我们在多个连续的控制任务上实施了多个方法的多次实例化,并发现我们能够显着提高策略绩效跨各种数据集尺寸。
translated by 谷歌翻译