• Corpus ID: 6142844

Shapechanger: Environments for Transfer Learning

@article{Arnold2017ShapechangerEF,
  title={Shapechanger: Environments for Transfer Learning},
  author={S{\'e}bastien M. R. Arnold and Tsam Kiu Pun and Th{\'e}o-Tim J. Denisart and Francisco J. Valero Cuevas},
  journal={ArXiv},
  year={2017},
  volume={abs/1709.05070}
}
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 

Figures from this paper

References

SHOWING 1-6 OF 6 REFERENCES

Sim-to-Real Robot Learning from Pixels with Progressive Nets

This work proposes using progressive networks to bridge the reality gap and transfer learned policies from simulation to the real world, and presents an early demonstration of this approach with a number of experiments in the domain of robot manipulation that focus on bridging thereality gap.

Tendon-driven control of biomechanical and robotic systems: A path integral reinforcement learning approach

We apply path integral reinforcement learning to a biomechanically accurate dynamics model of the index finger and then to the Anatomically Correct Testbed (ACT) robotic hand. We illustrate the

OpenAI Gym

This whitepaper discusses the components of OpenAI Gym and the design decisions that went into the software.

Trust Region Policy Optimization

A method for optimizing control policies, with guaranteed monotonic improvement, by making several approximations to the theoretically-justified scheme, called Trust Region Policy Optimization (TRPO).

MuJoCo: A physics engine for model-based control

A new physics engine tailored to model-based control, based on the modern velocity-stepping approach which avoids the difficulties with spring-dampers, which can compute both forward and inverse dynamics.

Neuromorphic meets neuromechanics, part II: the role of fusimotor drive

It is demonstrated that these fundamental features of spinal afferentation sufficed to produce muscle function, and the Neuro–mechano–morphic system is a working prototype of a robust biomorphic controller for compliant robotic limbs and exoskeletons.