Corpus ID: 232135324

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

@article{Ghadirzadeh2021BayesianMF,
  title={Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms},
  author={A. Ghadirzadeh and X. Chen and Petra Poklukar and Chelsea Finn and M{\aa}rten Bj{\"o}rkman and D. Kragic},
  journal={ArXiv},
  year={2021},
  volume={abs/2103.03697}
}
Reinforcement learning methods can achieve significant performance but require a large amount of training data collected on the same robotic platform. A policy trained with expensive data is rendered useless after making even a minor change to the robot hardware. In this paper, we address the challenging problem of adapting a policy, trained to perform a task, to a novel robotic hardware platform given only few demonstrations of robot motion trajectories on the target robot. We formulate it as… Expand

Figures from this paper

References

SHOWING 1-10 OF 49 REFERENCES
Hardware Conditioned Policies for Multi-Robot Transfer Learning
RoboNet: Large-Scale Multi-Robot Learning
Probabilistic Active Meta-Learning
Meta Reinforcement Learning for Sim-to-real Domain Adaptation
Learning modular neural network policies for multi-task and multi-robot transfer
Deep visual foresight for planning robot motion
Probabilistic Model-Agnostic Meta-Learning
...
1
2
3
4
5
...