Abstract
Observational learning requires an agent to learn to perform a task by referencing only observations of the performed task. This work investigates the equivalent setting in real-world robot learning where access to hand-designed rewards and demonstrator actions are not assumed. To address this data-constrained setting, this work presents a planning-based Inverse Reinforcement Learning (IRL) algorithm for world modeling from observation and interaction alone. Experiments conducted entirely in the real-world demonstrate that this paradigm is effective for learning image-based manipulation tasks from scratch in under an hour, without assuming prior knowledge, pre-training, or data of any kind beyond task observations. Moreover, this work demonstrates that the learned world model representation is capable of online transfer learning in the real-world from scratch. In comparison to existing approaches, including IRL, RL, and Behavior Cloning (BC), which have more restrictive assumptions, the proposed approach demonstrates significantly greater sample efficiency and success rates, enabling a practical path forward for online world modeling and planning from observation and interaction. Videos and more at: this https URL.
Abstract (translated)
观察学习要求智能体通过仅参考完成任务的观测来学会执行任务。这项工作研究了真实世界中机器人学习中的等效设定，在此场景下，不假设可以获得人为设计的奖励和展示者的动作数据。为了解决这种数据受限的情况，该研究提出了一种基于规划的逆向强化学习（IRL）算法，仅通过观察和互动进行世界建模。 在完全真实世界的实验中证明了这一范式能够从零开始，在不到一小时内有效学会基于图像的操作任务，并且不需要任何先验知识、预训练或任何形式的数据。此外，该研究还展示了所学得的世界模型表示能够在现实世界中实现从零开始的在线迁移学习。 与现有的方法（包括IRL、强化学习和行为克隆）相比，这些现有方法假设有更多的限制性假设，所提出的方法在样本效率和成功率方面表现出显著优势，从而为通过观察和互动进行实时世界建模和规划提供了一条实用路径。更多视频和其他信息请访问：[此处插入URL]。
URL
https://arxiv.org/abs/2602.24121
