SENSOR：通过主动传感模仿第三人称专家的行为
SENSOR: Imitate Third-Person Expert's Behaviors via Active Sensoring
AI总结：
针对视觉模仿学习中智能体与第三人称专家视角错位的问题，本文提出基于模型的SENSOR框架，通过联合学习世界模型、传感器策略和运动策略实现主动视角调整，并在视觉运动任务中优于多数基线。
摘要：
在许多真实世界的视觉模仿学习（IL）场景中，智能体与专家的视角之间存在错位，这可能导致模仿失败。以往方法通常通过域对齐来解决该问题，这会产生额外的计算和存储成本，而且这些方法无法处理视角差距过大的“困难情况”。为缓解上述问题，我们在视觉IL设置中引入主动传感，并提出了一种基于模型的SENSory imitatOR（SENSOR），用于自动改变智能体视角以匹配专家视角。SENSOR联合学习用于捕捉隐状态动态的世界模型、用于控制相机的传感器策略，以及用于控制智能体的运动策略。在视觉运动任务上的实验表明，SENSOR能够高效模拟专家的视角和策略，并且性能优于大多数基线方法。
英文摘要：
In many real-world visual Imitation Learning (IL) scenarios, there is a misalignment between the agent's and the expert's perspectives, which might lead to the failure of imitation. Previous methods have generally solved this problem by domain alignment, which incurs extra computation and storage costs, and these methods fail to handle the \textit{hard cases} where the viewpoint gap is too large. To alleviate the above problems, we introduce active sensoring in the visual IL setting and propose a model-based SENSory imitatOR (SENSOR) to automatically change the agent's perspective to match the expert's. SENSOR jointly learns a world model to capture the dynamics of latent states, a sensor policy to control the camera, and a motor policy to control the agent. Experiments on visual locomotion tasks show that SENSOR can efficiently simulate the expert's perspective and strategy, and outperforms most baseline methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
