Shapechanger: Environments for Transfer Learning
Published in
arXiv.org(2017)External Links:
TL
TL;DR
Shapechanger, a library for transfer reinforcement learning specifically designed for robotic tasks, considers 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.
Abstract
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: this https URL
References6 items
1
Neuromorphic meets neuromechanics, part II: the role of fusimotor drive
2
Sim-to-Real Robot Learning from Pixels with Progressive Nets
3
OpenAI Gym
4
Trust Region Policy Optimization
5