SIM到现实的转移是机器人增强学习的强大范式。在模拟中训练政策的能力可以以低成本快速探索和大规模数据收集。但是，机器人策略的SIM到现实转移的先前工作通常不涉及任何人类机器人的相互作用，因为准确模拟人类行为是一个空旷的问题。在这项工作中，我们的目标是利用模拟的力量来训练熟练在部署时与人类互动的机器人政策。但是有一个鸡肉和鸡蛋问题 - 我们如何收集人与物理机器人互动的例子，以在模拟中对人类行为进行建模，而没有已经有能够与人相互作用的机器人？我们提出的方法，即迭代-SIM-to-real（I-S2R），试图解决这个问题。 I-S2R引导程序来自一个简单的人类行为模型和在模拟和在现实世界中部署的训练之间的交替。在每次迭代中，人类行为模型和政策都得到了完善。我们在现实世界的机器人乒乓球环境中评估我们的方法，该机器人的目标是尽可能长时间与人类玩家合作。乒乓球是一项高速，充满活力的任务，要求两名球员对彼此的举动迅速做出反应，从而使测试床具有挑战性，以研究人类机器人互动。我们在一个工业机器人手臂上介绍了结果，该机器人能够与人类球员合作打乒乓球，平均获得22次连续击球的集会，充其量只有150个。此外，对于80％的球员来说，与SIM-TO-REAL（S2R）基线相比，拉力长度长70％至175％。有关我们系统中的视频，请参见https://sites.google.com/view/is2r。

从意外的外部扰动中恢复的能力是双模型运动的基本机动技能。有效的答复包括不仅可以恢复平衡并保持稳定性的能力，而且在平衡恢复物质不可行时，也可以保证安全的方式。对于与双式运动有关的机器人，例如人形机器人和辅助机器人设备，可帮助人类行走，设计能够提供这种稳定性和安全性的控制器可以防止机器人损坏或防止伤害相关的医疗费用。这是一个具有挑战性的任务，因为它涉及用触点产生高维，非线性和致动系统的高动态运动。尽管使用基于模型和优化方法的前进方面，但诸如广泛领域知识的要求，诸如较大的计算时间和有限的动态变化的鲁棒性仍然会使这个打开问题。在本文中，为了解决这些问题，我们开发基于学习的算法，能够为两种不同的机器人合成推送恢复控制政策：人形机器人和有助于双模型运动的辅助机器人设备。我们的工作可以分为两个密切相关的指示：1）学习人形机器人的安全下降和预防策略，2）使用机器人辅助装置学习人类的预防策略。为实现这一目标，我们介绍了一套深度加强学习（DRL）算法，以学习使用这些机器人时提高安全性的控制策略。

学习玩乒乓球是机器人的一个具有挑战性的任务，作为所需的各种笔画。最近的进展表明，深度加强学习（RL）能够在模拟环境中成功地学习最佳动作。然而，由于高勘探努力，RL在实际情况中的适用性仍然有限。在这项工作中，我们提出了一个现实的模拟环境，其中多种模型是为球的动态和机器人的运动学而建立的。代替训练端到端的RL模型，提出了一种具有TD3骨干的新的政策梯度方法，以基于击球时间基于球的预测状态来学习球拍笔划。在实验中，我们表明，所提出的方法显着优于仿真中现有的RL方法。此外，将域从仿真跨越现实，我们采用了一个有效的再培训方法，并在三种实际情况下测试。由此产生的成功率为98％，距离误差约为24.9厘米。总培训时间约为1.5小时。

我们研究了复杂几何物体的机器人堆叠问题。我们提出了一个挑战和多样化的这些物体，这些物体被精心设计，以便要求超出简单的“拾取”解决方案之外的策略。我们的方法是加强学习（RL）方法与基于视觉的互动政策蒸馏和模拟到现实转移相结合。我们的学习政策可以有效地处理现实世界中的多个对象组合，并展示各种各样的堆叠技能。在一个大型的实验研究中，我们调查在模拟中学习这种基于视觉的基于视觉的代理的选择，以及对真实机器人的最佳转移产生了什么影响。然后，我们利用这些策略收集的数据并通过离线RL改善它们。我们工作的视频和博客文章作为补充材料提供。

Imitation learning techniques aim to mimic human behavior in a given task. An agent (a learning machine) is trained to perform a task from demonstrations by learning a mapping between observations and actions. The idea of teaching by imitation has been around for many years, however, the field is gaining attention recently due to advances in computing and sensing as well as rising demand for intelligent applications. The paradigm of learning by imitation is gaining popularity because it facilitates teaching complex tasks with minimal expert knowledge of the tasks. Generic imitation learning methods could potentially reduce the problem of teaching a task to that of providing demonstrations; without the need for explicit programming or designing reward functions specific to the task. Modern sensors are able to collect and transmit high volumes of data rapidly, and processors with high computational power allow fast processing that maps the sensory data to actions in a timely manner. This opens the door for many potential AI applications that require real-time perception and reaction such as humanoid robots, self-driving vehicles, human computer interaction and computer games to name a few. However, specialized algorithms are needed to effectively and robustly learn models as learning by imitation poses its own set of challenges. In this paper, we survey imitation learning methods and present design options in different steps of the learning process. We introduce a background and motivation for the field as well as highlight challenges specific to the imitation problem. Methods for designing and evaluating imitation learning tasks are categorized and reviewed. Special attention is given to learning methods in robotics and games as these domains are the most popular in the literature and provide a wide array of problems and methodologies. We extensively discuss combining imitation learning approaches using different sources and methods, as well as incorporating other motion learning methods to enhance imitation. We also discuss the potential impact on industry, present major applications and highlight current and future research directions.

强化学习（RL）算法有望为机器人系统实现自主技能获取。但是，实际上，现实世界中的机器人RL通常需要耗时的数据收集和频繁的人类干预来重置环境。此外，当部署超出知识的设置超出其学习的设置时，使用RL学到的机器人政策通常会失败。在这项工作中，我们研究了如何通过从先前看到的任务中收集的各种离线数据集的有效利用来应对这些挑战。当面对一项新任务时，我们的系统会适应以前学习的技能，以快速学习执行新任务并将环境返回到初始状态，从而有效地执行自己的环境重置。我们的经验结果表明，将先前的数据纳入机器人增强学习中可以实现自主学习，从而大大提高了学习的样本效率，并可以更好地概括。

机器人和与世界相互作用或互动的机器人和智能系统越来越多地被用来自动化各种任务。这些系统完成这些任务的能力取决于构成机器人物理及其传感器物体的机械和电气部件，例如，感知算法感知环境，并计划和控制算法以生产和控制算法来生产和控制算法有意义的行动。因此，通常有必要在设计具体系统时考虑这些组件之间的相互作用。本文探讨了以端到端方式对机器人系统进行任务驱动的合作的工作，同时使用推理或控制算法直接优化了系统的物理组件以进行任务性能。我们首先考虑直接优化基于信标的本地化系统以达到本地化准确性的问题。设计这样的系统涉及将信标放置在整个环境中，并通过传感器读数推断位置。在我们的工作中，我们开发了一种深度学习方法，以直接优化信标的放置和位置推断以达到本地化精度。然后，我们将注意力转移到了由任务驱动的机器人及其控制器优化的相关问题上。在我们的工作中，我们首先提出基于多任务增强学习的数据有效算法。我们的方法通过利用能够在物理设计的空间上概括设计条件的控制器，有效地直接优化了物理设计和控制参数，以直接优化任务性能。然后，我们对此进行跟进，以允许对离散形态参数（例如四肢的数字和配置）进行优化。最后，我们通过探索优化的软机器人的制造和部署来得出结论。

我们解决了使四足机器人能够使用强化学习在现实世界中执行精确的射击技巧的问题。开发算法使腿部机器人能够向给定的目标射击足球，这是一个具有挑战性的问题，它将机器人运动控制和计划结合到一项任务中。为了解决这个问题，我们需要考虑控制动态腿部机器人期间的动态限制和运动稳定性。此外，我们需要考虑运动计划，以在地面上射击难以模拟的可变形球，并不确定摩擦到所需的位置。在本文中，我们提出了一个层次结构框架，该框架利用深厚的强化学习来训练（a）强大的运动控制政策，可以跟踪任意动议，以及（b）一项计划政策，以决定所需的踢球运动将足球射击到目标。我们将提议的框架部署在A1四足动物机器人上，使其能够将球准确地射击到现实世界中的随机目标。

Figure 1: A five-fingered humanoid hand trained with reinforcement learning manipulating a block from an initial configuration to a goal configuration using vision for sensing.

Inspired by progress in large-scale language modeling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. In this report we describe the model and the data, and document the current capabilities of Gato.

Reinforcement learning holds the promise of enabling autonomous robots to learn large repertoires of behavioral skills with minimal human intervention. However, robotic applications of reinforcement learning often compromise the autonomy of the learning process in favor of achieving training times that are practical for real physical systems. This typically involves introducing hand-engineered policy representations and human-supplied demonstrations. Deep reinforcement learning alleviates this limitation by training general-purpose neural network policies, but applications of direct deep reinforcement learning algorithms have so far been restricted to simulated settings and relatively simple tasks, due to their apparent high sample complexity. In this paper, we demonstrate that a recent deep reinforcement learning algorithm based on offpolicy training of deep Q-functions can scale to complex 3D manipulation tasks and can learn deep neural network policies efficiently enough to train on real physical robots. We demonstrate that the training times can be further reduced by parallelizing the algorithm across multiple robots which pool their policy updates asynchronously. Our experimental evaluation shows that our method can learn a variety of 3D manipulation skills in simulation and a complex door opening skill on real robots without any prior demonstrations or manually designed representations.

Policy search methods can allow robots to learn control policies for a wide range of tasks, but practical applications of policy search often require hand-engineered components for perception, state estimation, and low-level control. In this paper, we aim to answer the following question: does training the perception and control systems jointly end-toend provide better performance than training each component separately? To this end, we develop a method that can be used to learn policies that map raw image observations directly to torques at the robot's motors. The policies are represented by deep convolutional neural networks (CNNs) with 92,000 parameters, and are trained using a guided policy search method, which transforms policy search into supervised learning, with supervision provided by a simple trajectory-centric reinforcement learning method. We evaluate our method on a range of real-world manipulation tasks that require close coordination between vision and control, such as screwing a cap onto a bottle, and present simulated comparisons to a range of prior policy search methods.

We present a retrospective on the state of Embodied AI research. Our analysis focuses on 13 challenges presented at the Embodied AI Workshop at CVPR. These challenges are grouped into three themes: (1) visual navigation, (2) rearrangement, and (3) embodied vision-and-language. We discuss the dominant datasets within each theme, evaluation metrics for the challenges, and the performance of state-of-the-art models. We highlight commonalities between top approaches to the challenges and identify potential future directions for Embodied AI research.

物理模拟器在安全，不受约束的环境中方便学习加强学习政策表现出了巨大的希望。但是，由于现实差距，将获得的知识转移到现实世界可能会具有挑战性。为此，最近已经提出了几种方法来自动调整具有后验分布的实际数据，以在训练时与域随机化一起使用。这些方法已被证明在不同的设置和假设下适用于各种机器人任务。然而，现有文献缺乏对转移性能和实际数据效率的现有自适应域随机方法的详尽比较。在这项工作中，我们为离线和在线方法（Simopt，Bayrn，Droid，Dropo）提供了一个开放的基准，以阐明最适合每个设置和手头的任务。我们发现，在线方法受到下一次迭代的当前学会策略的质量受到限制，而离线方法有时可能会在使用开环命令中模拟中重播轨迹时失败。所使用的代码将在https://github.com/gabrieletiboni/adr-benchmark上发布。

当前，随机化是用于机器人技术中数据驱动的学习算法的SIM2REAL传输中广泛使用的方法。尽管如此，大多数SIM2REAL研究报告了特定随机技术的结果，并且通常是在高度定制的机器人系统上，因此很难系统地评估不同的随机方法。为了解决这个问题，我们为机器人触及余量操纵器任务定义了易于制作的实验设置，该设置可以作为比较的基准。我们将四个随机策略与模拟和真实机器人中的三个随机参数进行比较。我们的结果表明，更多的随机化有助于SIM2REAL转移，但它也可能损害算法在模拟中找到良好策略的能力。完全随机的仿真和微调显示出差异化的结果，并且比测试的其他方法更好地转化为实际机器人。

机器人将机器人的无缝集成到人类环境需要机器人来学习如何使用现有的人类工具。学习工具操纵技能的目前方法主要依赖于目标机器人环境中提供的专家演示，例如，通过手动引导机器人操纵器或通过远程操作。在这项工作中，我们介绍了一种自动化方法，取代了一个专家演示，用YouTube视频来学习工具操纵策略。主要贡献是双重的。首先，我们设计一个对齐过程，使模拟环境与视频中观察到的真实世界。这是作为优化问题，找到刀具轨迹的空间对齐，以最大化环境给出的稀疏目标奖励。其次，我们描述了一种专注于工具的轨迹而不是人类的运动的模仿学习方法。为此，我们将加强学习与优化过程相结合，以基于对准环境中的工具运动来找到控制策略和机器人的放置。我们展示了仿真中的铲子，镰刀和锤子工具的建议方法，并展示了训练有素的政策对真正的弗兰卡·埃米卡熊猫机器人示范的卫生政策的有效性。

Legged robots pose one of the greatest challenges in robotics. Dynamic and agile maneuvers of animals cannot be imitated by existing methods that are crafted by humans. A compelling alternative is reinforcement learning, which requires minimal craftsmanship and promotes the natural evolution of a control policy. However, so far, reinforcement learning research for legged robots is mainly limited to simulation, and only few and comparably simple examples have been deployed on real systems. The primary reason is that training with real robots, particularly with dynamically balancing systems, is complicated and expensive. In the present work, we report a new method for training a neural network policy in simulation and transferring it to a state-of-the-art legged system, thereby we leverage fast, automated, and cost-effective data generation schemes. The approach is applied to the ANYmal robot, a sophisticated medium-dog-sized quadrupedal system. Using policies trained in simulation, the quadrupedal machine achieves locomotion skills that go beyond what had been achieved with prior methods: ANYmal is capable of precisely and energy-efficiently following high-level body velocity commands, running faster than ever before, and recovering from falling even in complex configurations.

While reinforcement learning (RL) has become a more popular approach for robotics, designing sufficiently informative reward functions for complex tasks has proven to be extremely difficult due their inability to capture human intent and policy exploitation. Preference based RL algorithms seek to overcome these challenges by directly learning reward functions from human feedback. Unfortunately, prior work either requires an unreasonable number of queries implausible for any human to answer or overly restricts the class of reward functions to guarantee the elicitation of the most informative queries, resulting in models that are insufficiently expressive for realistic robotics tasks. Contrary to most works that focus on query selection to \emph{minimize} the amount of data required for learning reward functions, we take an opposite approach: \emph{expanding} the pool of available data by viewing human-in-the-loop RL through the more flexible lens of multi-task learning. Motivated by the success of meta-learning, we pre-train preference models on prior task data and quickly adapt them for new tasks using only a handful of queries. Empirically, we reduce the amount of online feedback needed to train manipulation policies in Meta-World by 20$\times$, and demonstrate the effectiveness of our method on a real Franka Panda Robot. Moreover, this reduction in query-complexity allows us to train robot policies from actual human users. Videos of our results and code can be found at https://sites.google.com/view/few-shot-preference-rl/home.

For an autonomous agent to fulfill a wide range of user-specified goals at test time, it must be able to learn broadly applicable and general-purpose skill repertoires. Furthermore, to provide the requisite level of generality, these skills must handle raw sensory input such as images. In this paper, we propose an algorithm that acquires such general-purpose skills by combining unsupervised representation learning and reinforcement learning of goal-conditioned policies. Since the particular goals that might be required at test-time are not known in advance, the agent performs a self-supervised "practice" phase where it imagines goals and attempts to achieve them. We learn a visual representation with three distinct purposes: sampling goals for self-supervised practice, providing a structured transformation of raw sensory inputs, and computing a reward signal for goal reaching. We also propose a retroactive goal relabeling scheme to further improve the sample-efficiency of our method. Our off-policy algorithm is efficient enough to learn policies that operate on raw image observations and goals for a real-world robotic system, and substantially outperforms prior techniques. * Equal contribution. Order was determined by coin flip.