We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target task. WAPPO approximates and minimizes the Wasserstein-1 distance between the distributions of features from source and target domains via a novel Wasserstein Confusion objective. WAPPO outperforms the prior state-of-the-art in visual transfer and successfully transfers policies across Visual Cartpole and two instantiations of 16 OpenAI Procgen environments.
@article{arxiv.2006.03465,
title = {Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion},
author = {Josh Roy and George Konidaris},
journal= {arXiv preprint arXiv:2006.03465},
year = {2020}
}