Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience

@article{Chebotar2018ClosingTS,
  title={Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience},
  author={Yevgen Chebotar and Ankur Handa and Viktor Makoviychuk and Miles Macklin and Jan Issac and Nathan D. Ratliff and Dieter Fox},
  journal={2019 International Conference on Robotics and Automation (ICRA)},
  year={2018},
  pages={8973-8979}
}
We consider the problem of transferring policies to the real world by training on a distribution of simulated scenarios. Rather than manually tuning the randomization of simulations, we adapt the simulation parameter distribution using a few real world roll-outs interleaved with policy training. In doing so, we are able to change the distribution of simulations to improve the policy transfer by matching the policy behavior in simulation and the real world. We show that policies trained with our… CONTINUE READING

Similar Papers

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 19 CITATIONS

References

Publications referenced by this paper.
SHOWING 1-10 OF 45 REFERENCES

Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system

  • 2018 IEEE International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR)
  • 2018
VIEW 1 EXCERPT

Domain randomization for transferring deep neural networks from simulation to the real world

  • 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2017
VIEW 3 EXCERPTS