Learning generalizable policies that can adapt to unseen environments remains challenging in visual Reinforcement Learning (RL). Existing approaches try to acquire a robust representation via diversifying the appearances of in-domain observations for better generalization. Limited by the specific observations of the environment, these methods ignore the possibility of exploring diverse real-world image datasets. In this paper, we investigate how a visual RL agent would benefit from the off-the-shelf visual representations. Surprisingly, we find that the early layers in an ImageNet pre-trained ResNet model could provide rather generalizable representations for visual RL. Hence, we propose Pre-trained Image Encoder for Generalizable visual reinforcement learning (PIE-G), a simple yet effective framework that can generalize to the unseen visual scenarios in a zero-shot manner. Extensive experiments are conducted on DMControl Generalization Benchmark, DMControl Manipulation Tasks, Drawer World, and CARLA to verify the effectiveness of PIE-G. Empirical evidence suggests PIE-G improves sample efficiency and significantly outperforms previous state-of-the-art methods in terms of generalization performance. In particular, PIE-G boasts a 55% generalization performance gain on average in the challenging video background setting. Project Page: https://sites.google.com/view/pie-g/home.

We revisit a simple Learning-from-Scratch baseline for visuo-motor control that uses data augmentation and a shallow ConvNet. We find that this baseline has competitive performance with recent methods that leverage frozen visual representations trained on large-scale vision datasets.

Humans use all of their senses to accomplish different tasks in everyday activities. In contrast, existing work on robotic manipulation mostly relies on one, or occasionally two modalities, such as vision and touch. In this work, we systematically study how visual, auditory, and tactile perception can jointly help robots to solve complex manipulation tasks. We build a robot system that can see with a camera, hear with a contact microphone, and feel with a vision-based tactile sensor, with all three sensory modalities fused with a self-attention model. Results on two challenging tasks, dense packing and pouring, demonstrate the necessity and power of multisensory perception for robotic manipulation: vision displays the global status of the robot but can often suffer from occlusion, audio provides immediate feedback of key moments that are even invisible, and touch offers precise local geometry for decision making. Leveraging all three modalities, our robotic system significantly outperforms prior methods.

A critical challenge in multi-agent reinforcement learning(MARL) is for multiple agents to efficiently accomplish complex, long-horizon tasks. The agents often have difficulties in cooperating on common goals, dividing complex tasks, and planning through several stages to make progress. We propose to address these challenges by guiding agents with programs designed for parallelization, since programs as a representation contain rich structural and semantic information, and are widely used as abstractions for long-horizon tasks. Specifically, we introduce Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance(E-MAPP), a novel framework that leverages parallel programs to guide multiple agents to efficiently accomplish goals that require planning over $10+$ stages. E-MAPP integrates the structural information from a parallel program, promotes the cooperative behaviors grounded in program semantics, and improves the time efficiency via a task allocator. We conduct extensive experiments on a series of challenging, long-horizon cooperative tasks in the Overcooked environment. Results show that E-MAPP outperforms strong baselines in terms of the completion rate, time efficiency, and zero-shot generalization ability by a large margin.

可以测量接触物体的3D几何形状的基于视觉的触觉传感器对于机器人执行灵巧的操纵任务至关重要。但是，现有的传感器通常很复杂，可以制造和细腻以扩展。在这项工作中，我们从小地利用了半透明弹性体的反射特性来设计一种名为DTACT的强大，低成本且易于制作的触觉传感器。DTACT从捕获的触觉图像中所示的黑暗中精确测量了高分辨率3D几何形状，仅具有单个图像进行校准。与以前的传感器相反，在各种照明条件下，DTACT是可靠的。然后，我们构建了具有非平面接触表面的DTACT原型，并以最少的额外努力和成本。最后，我们执行了两项智能机器人任务，包括使用DTACT进行姿势估计和对象识别，其中DTACT在应用中显示出巨大的潜力。

机器人可以通过仅仅在单个对象实例上抓住姿势的证明，以任意姿势操纵类别内看不见的对象？在本文中，我们尝试通过使用Useek（一种无监督的SE（3） - 等级关键点方法来应对这一有趣的挑战，该方法在类别中享受整个实例的对齐方式，以执行可推广的操作。 USEEK遵循教师学生的结构，将无监督的关键点发现和SE（3） - 等级关键点检测解除。使用Useek，机器人可以以有效且可解释的方式推断与任务相关的对象框架，从而使任何类别内对象都从任何姿势中操纵。通过广泛的实验，我们证明了Useek产生的关键点具有丰富的语义，因此成功地将功能知识从演示对象转移到了新颖的对象。与其他进行操作的对象表示相比，面对大类别内形状差异，更健壮的演示率更有限，并且在推理时间更有效。

将监督学习的力量（SL）用于更有效的强化学习（RL）方法，这是最近的趋势。我们通过交替在线RL和离线SL来解决稀疏奖励目标条件问题，提出一种新颖的阶段方法。在在线阶段，我们在离线阶段进行RL培训并收集推出数据，我们对数据集的这些成功轨迹执行SL。为了进一步提高样本效率，我们在在线阶段采用其他技术，包括减少任务以产生更可行的轨迹和基于价值的基于价值的内在奖励，以减轻稀疏的回报问题。我们称此总体算法为阶段性的自我模拟还原（Pair）。对稀疏的奖励目标机器人控制问题（包括具有挑战性的堆叠任务），对基本上优于非强调RL和Phasic SL基线。 Pair是第一个学习堆叠6个立方体的RL方法，只有0/1成功从头开始奖励。

我们向多人3D运动轨迹预测提出了一种新颖的框架。我们的主要观察是，人类的行动和行为可能高度依赖于其他人。因此，不是以隔离预测每个人类姿势轨迹，我们引入了一种多范围变压器模型，该模型包含用于各个运动的局部运动和用于社交交互的全局范围编码器。然后，通过将相应的姿势作为查询来参加本地和全球范围编码器特征，对变压器解码器对每个人进行预测。我们的模型不仅优于长期3D运动预测的最先进的方法，而且还产生了不同的社交互动。更有趣的是，我们的模型甚至可以通过自动将人分为不同的交互组来同时预测15人运动。具有代码的项目页面可在https://jiahunwang.github.io/mrt/处获得。

保守主义的概念导致了离线强化学习（RL）的重要进展，其中代理从预先收集的数据集中学习。但是，尽可能多的实际方案涉及多个代理之间的交互，解决更实际的多代理设置中的离线RL仍然是一个开放的问题。鉴于最近将Online RL算法转移到多代理设置的成功，可以预期离线RL算法也将直接传输到多代理设置。令人惊讶的是，当基于保守的算法应用于多蛋白酶的算法时，性能显着降低了越来越多的药剂。为了减轻劣化，我们确定了价值函数景观可以是非凹形的关键问题，并且策略梯度改进容易出现本地最优。自从任何代理人的次优政策可能导致不协调的全球失败以来，多个代理人会加剧问题。在这种直觉之后，我们提出了一种简单而有效的方法，脱机多代理RL与演员整流（OMAR），通过有效的一阶政策梯度和Zeroth订单优化方法为演员更好地解决这一关键挑战优化保守值函数。尽管简单，奥马尔显着优于强大的基线，在多售后连续控制基准测试中具有最先进的性能。

演奏家以热情，诗歌和非凡的技术能力弹奏钢琴。正如李斯特（Liszt）所说（一个演奏家）必须呼唤气味和开花，并呼吸生命的呼吸。可以弹钢琴的最强机器人是基于专业机器人手/钢琴和硬编码计划算法的组合。与此相反，在本文中，我们演示了代理如何直接从机器可读的音乐得分中学习，以使用SCRATCH的增强钢琴学习（RL）在模拟的钢琴上弹奏钢琴。我们证明RL代理不仅可以找到正确的关键位置，还可以处理各种节奏，音量和指法，要求。我们通过使用接触式的奖励和新的任务课程来实现这一目标。最后，我们通过仔细研究重要方面来实现此类学习算法，并有可能阐明朝这个方向上的未来研究。