@article{Kim_Park_2018, title={Imitation Learning via Kernel Mean Embedding}, volume={32}, url={https://ojs.aaai.org/index.php/AAAI/article/view/11720}, DOI={10.1609/aaai.v32i1.11720}, abstractNote={ <p> Imitation learning refers to the problem where an agent learns a policy that mimics the demonstration provided by the expert, without any information on the cost function of the environment. Classical approaches to imitation learning usually rely on a restrictive class of cost functions that best explains the expert’s demonstration, exemplified by linear functions of pre-defined features on states and actions. We show that the kernelization of a classical algorithm naturally reduces the imitation learning to a distribution learning problem, where the imitation policy tries to match the state-action visitation distribution of the expert. Closely related to our approach is the recent work on leveraging generative adversarial networks (GANs) for imitation learning, but our reduction to distribution learning is much simpler, robust to scarce expert demonstration, and sample efficient. We demonstrate the effectiveness of our approach on a wide range of high-dimensional control tasks. </p> }, number={1}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Kim, Kee-Eung and Park, Hyun Soo}, year={2018}, month={Apr.} }