Corpus ID: 204743943

Single Episode Policy Transfer in Reinforcement Learning

@article{Yang2019SingleEP,
  title={Single Episode Policy Transfer in Reinforcement Learning},
  author={Jiachen Yang and Brenden K. Petersen and Hongyuan Zha and Daniel Faissol},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.07719}
}
  • Jiachen Yang, Brenden K. Petersen, +1 author Daniel Faissol
  • Published in ICLR 2019
  • Mathematics, Computer Science
  • ArXiv
  • Transfer and adaptation to new unknown environmental dynamics is a key challenge for reinforcement learning (RL). An even greater challenge is performing near-optimally in a single attempt at test time, possibly without access to dense rewards, which is not addressed by current methods that require multiple experience rollouts for adaptation. To achieve single episode transfer in a family of environments with related dynamics, we propose a general algorithm that optimizes a probe and an… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 40 REFERENCES

    Human-level control through deep reinforcement learning

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Reinforcement Learning: An Introduction

    VIEW 13 EXCERPTS
    HIGHLY INFLUENTIAL

    Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Towards Multidrug Adaptive Therapy

    VIEW 1 EXCERPT

    Deep Reinforcement Learning and Simulation as a Path Toward Precision Medicine

    VIEW 2 EXCERPTS