Corpus ID: 49318805

Stagewise Safe Bayesian Optimization with Gaussian Processes

@inproceedings{Sui2018StagewiseSB,
  title={Stagewise Safe Bayesian Optimization with Gaussian Processes},
  author={Yanan Sui and Vincent Zhuang and Joel W. Burdick and Yisong Yue},
  booktitle={ICML},
  year={2018}
}
  • Yanan Sui, Vincent Zhuang, +1 author Yisong Yue
  • Published in ICML 2018
  • Computer Science, Mathematics
  • Enforcing safety is a key aspect of many problems pertaining to sequential decision making under uncertainty, which require the decisions made at every step to be both informative of the optimal decision and also safe. For example, we value both efficacy and comfort in medical therapy, and efficiency and safety in robotic control. We consider this problem of optimizing an unknown utility function with absolute feedback or preference feedback subject to unknown safety constraints. We develop an… CONTINUE READING

    Citations

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

    Safe Exploration for Interactive Machine Learning

    VIEW 5 EXCERPTS
    CITES RESULTS & BACKGROUND
    HIGHLY INFLUENCED

    Linear Stochastic Bandits Under Safety Constraints

    VIEW 2 EXCERPTS
    CITES METHODS & BACKGROUND

    Robust Regression for Safe Exploration in Control

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Safe Linear Thompson Sampling with Side Information.

    VIEW 3 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Safe Linear Stochastic Bandits

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 31 REFERENCES

    Safe Exploration in Markov Decision Processes

    VIEW 1 EXCERPT

    Safe Exploration of State and Action Spaces in Reinforcement Learning

    VIEW 1 EXCERPT