RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstration
This addresses the challenge of imitation learning in robotics when action information is unavailable, offering a more flexible approach, though it is incremental in combining existing techniques.
The paper tackles the problem of learning from a single observed demonstration without access to demonstrator actions, introducing RIDM, a novel paradigm that combines imitation from observation and reinforcement learning, and shows it performs favorably compared to a baseline in simulation and on a real UR5 robot arm.
Augmenting reinforcement learning with imitation learning is often hailed as a method by which to improve upon learning from scratch. However, most existing methods for integrating these two techniques are subject to several strong assumptions---chief among them that information about demonstrator actions is available. In this paper, we investigate the extent to which this assumption is necessary by introducing and evaluating reinforced inverse dynamics modeling (RIDM), a novel paradigm for combining imitation from observation (IfO) and reinforcement learning with no dependence on demonstrator action information. Moreover, RIDM requires only a single demonstration trajectory and is able to operate directly on raw (unaugmented) state features. We find experimentally that RIDM performs favorably compared to a baseline approach for several tasks in simulation as well as for tasks on a real UR5 robot arm. Experiment videos can be found at https://sites.google.com/view/ridm-reinforced-inverse-dynami.