Skip to yearly menu bar Skip to main content


Poster

A Bayesian Approach to Generative Adversarial Imitation Learning

Wonseok Jeon · Seokin Seo · Kee-Eung Kim

Room 517 AB #129

Keywords: [ Decision and Control ] [ Reinforcement Learning ] [ Markov Decision Processes ]


Abstract:

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 has shown to robustly learn to imitate even with scarce demonstration, one must still address the inherent challenge that 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.

Live content is unavailable. Log in and register to view live content