A Bayesian Approach to Generative Adversarial Imitation Learning

Wonseok Jeon, Seokin Seo, Kee-Eung Kim
2018 Neural Information Processing Systems  
Generative adversarial training for imitation learning has shown promising results on high-dimensional and continuous control tasks. This paradigm is based on reducing the imitation learning problem to the density matching problem, where the agent iteratively refines the policy to match the empirical state-action visitation frequency of the expert demonstration. Although this approach can robustly learn to imitate even with scarce demonstration, one must still address the inherent challenge
more » ... collecting trajectory samples in each iteration is a costly operation. To address this issue, we first propose a Bayesian formulation of generative adversarial imitation learning (GAIL), where the imitation policy and the cost function are represented as stochastic neural networks. Then, we show that we can significantly enhance the sample efficiency of GAIL leveraging the predictive density of the cost, on an extensive set of imitation learning tasks with high-dimensional states and actions.
dblp:conf/nips/JeonSK18 fatcat:obctzjpj2ndrhbcv3xgmix4seq