arXiv:1709.05070
Shapechanger: Environments for Transfer Learning
Shapechanger: Environments for Transfer Learning
著者: Sébastien M. R. Arnold, Tsam Kiu Pun, Théo-Tim J. Denisart, Francisco J. Valero-Cuevas
分類: cs.LG, cs.RO
原文アブストラクト
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/.