TR-BEACON: Shedding Light on Efficient Behavior Discovery in High-Dimensional Spaces with Bayesian Novelty Search over Trust Regions

Abstract

Novelty search (NS) algorithms automatically discover diverse system behaviors through simulations or experiments, often treating the system as a black box due to unknown input-output relationships. Previously, we introduced BEACON, a sample-efficient NS algorithm that uses probabilistic surrogate models to select inputs likely to produce novel behaviors. In this paper, we present TR-BEACON, a high-dimensional extension of BEACON that mitigates the curse of dimensionality by constructing local probabilistic models over a trust region whose geometry is adapted as information is gathered. Through numerical experiments, we demonstrate that TR-BEACON significantly outperforms state-of-the-art NS methods on high-dimensional problems, including a challenging robot maze navigation task.

PDF NeurIPSW OpenReview Semantic Scholar

Cite

Text

Tang et al. "TR-BEACON: Shedding Light on Efficient Behavior Discovery in High-Dimensional Spaces with Bayesian Novelty Search over Trust Regions." NeurIPS 2024 Workshops: BDU, 2024.

Markdown

[Tang et al. "TR-BEACON: Shedding Light on Efficient Behavior Discovery in High-Dimensional Spaces with Bayesian Novelty Search over Trust Regions." NeurIPS 2024 Workshops: BDU, 2024.](https://mlanthology.org/neuripsw/2024/tang2024neuripsw-trbeacon/)

BibTeX

@inproceedings{tang2024neuripsw-trbeacon,
  title     = {{TR-BEACON: Shedding Light on Efficient Behavior Discovery in High-Dimensional Spaces with Bayesian Novelty Search over Trust Regions}},
  author    = {Tang, Wei-Ting and Chakrabarty, Ankush and Paulson, Joel},
  booktitle = {NeurIPS 2024 Workshops: BDU},
  year      = {2024},
  url       = {https://mlanthology.org/neuripsw/2024/tang2024neuripsw-trbeacon/}
}