We present Shapechanger, a library for transfer reinforcement learning specifically designed for robotic tasks. We consider three types of knowledge transfer---from simulation to simulation, from simulation to real, and from real to real---and a wide range of tasks with continuous states and actions. Shapechanger is under active development and open-sourced at: https://github.com/seba-1511/shapechanger/.
@article{arxiv.1709.05070,
title = {Shapechanger: Environments for Transfer Learning},
author = {Sébastien M. R. Arnold and Tsam Kiu Pun and Théo-Tim J. Denisart and Francisco J. Valero-Cuevas},
journal= {arXiv preprint arXiv:1709.05070},
year = {2017}
}