Trajectory VAE for multi-modal imitation

Xiaoyu Lu, Jan Stuehmer, Katja Hofmann

Abstract:

We address the problem of imitating multi-modal expert demonstrations in sequential decision making problems. In many practical applications, for example video games, behavioural demonstrations are readily available that contain multi-modal structure not captured by typical existing imitation learning approaches. For example, differences in the observed players' behaviours may be representative of different underlying playstyles.

In this paper, we use a generative model to capture different emergent playstyles in an unsupervised manner, enabling the imitation of a diverse range of distinct behaviours. We utilise a variational autoencoder to learn an embedding of the different types of expert demonstrations on the trajectory level, and jointly learn a latent representation with a policy. In experiments on a range of 2D continuous control problems representative of Minecraft environments, we empirically demonstrate that our model can capture a multi-modal structured latent space from the demonstrated behavioural trajectories.

Keywords: imitation learning, latent variable model, variational autoencoder, diverse behaviour

TL;DR: A trajectory-VAE method for imitating multi-modal expert demonstrations in sequential decision making problems.