Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes

Taylor W. Killian, George Dimitri Konidaris, Finale Doshi-Velez

AAAI 2017 pp. 4949-4950

doi:10.1609/AAAI.V31I1.11065 /aaai/2017/killian2017aaai-robust/

Abstract

We introduce a new formulation of the Hidden Parameter Markov Decision Process (HiP-MDP), a framework for modeling families of related tasks using low-dimensional latent embeddings. Our new framework correctly models the joint uncertainty in the latent parameters and the state space. We also replace the original Gaussian Process-based model with a Bayesian Neural Network, enabling more scalable inference. Thus, we expand the scope of the HiP-MDP to applications with higher dimensions and more complex dynamics.

PDF AAAI Semantic Scholar

Cite

Text

Killian et al. "Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2017. doi:10.1609/AAAI.V31I1.11065

Markdown

[Killian et al. "Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes." AAAI Conference on Artificial Intelligence, 2017.](https://mlanthology.org/aaai/2017/killian2017aaai-robust/) doi:10.1609/AAAI.V31I1.11065

BibTeX

@inproceedings{killian2017aaai-robust,
  title     = {{Robust and Efficient Transfer Learning with Hidden Parameter Markov Decision Processes}},
  author    = {Killian, Taylor W. and Konidaris, George Dimitri and Doshi-Velez, Finale},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2017},
  pages     = {4949-4950},
  doi       = {10.1609/AAAI.V31I1.11065},
  url       = {https://mlanthology.org/aaai/2017/killian2017aaai-robust/}
}