Recent Advances in Imitation Learning from Observation
This is an incremental review that addresses the problem of enabling imitation learning from abundant but action-limited resources for researchers and practitioners in robotics and AI.
The paper reviews imitation learning from observation (IfO), where an agent learns tasks using only state information from experts, such as videos, without requiring action data, to leverage existing resources like online videos.
Imitation learning is the process by which one agent tries to learn how to perform a certain task using information generated by another, often more-expert agent performing that same task. Conventionally, the imitator has access to both state and action information generated by an expert performing the task (e.g., the expert may provide a kinesthetic demonstration of object placement using a robotic arm). However, requiring the action information prevents imitation learning from a large number of existing valuable learning resources such as online videos of humans performing tasks. To overcome this issue, the specific problem of imitation from observation (IfO) has recently garnered a great deal of attention, in which the imitator only has access to the state information (e.g., video frames) generated by the expert. In this paper, we provide a literature review of methods developed for IfO, and then point out some open research problems and potential future work.