We study risk-sensitive imitation learning where the agent's goal is to perform at least as well as the expert in terms of a risk profile. We first formulate our risk-sensitive imitation learning setting. We consider the generative adversarial approach to imitation learning (GAIL) and derive an optimization problem for our formulation, which we call it risk-sensitive GAIL (RS-GAIL). We then derive two different versions of our RS-GAIL optimization problem that aim at matching the risk profiles of the agent and the expert w.r.t. Jensen-Shannon (JS) divergence and Wasserstein distance, and develop risk-sensitive generative adversarial imitation learning algorithms based on these optimization problems. We evaluate the performance of our algorithms and compare them with GAIL and the risk-averse imitation learning (RAIL) algorithms in two MuJoCo and two OpenAI classical control tasks.
@article{arxiv.1808.04468,
title = {Risk-Sensitive Generative Adversarial Imitation Learning},
author = {Jonathan Lacotte and Mohammad Ghavamzadeh and Yinlam Chow and Marco Pavone},
journal= {arXiv preprint arXiv:1808.04468},
year = {2018}
}