Task Scoping for Efficient Planning in Open Worlds (Student Abstract)

Nishanth Kumar, Michael Fishman, Natasha Danas, Stefanie Tellex, Michael Littman, George Konidaris

AAAI 2020 pp. 13845-13846

doi:10.1609/AAAI.V34I10.7195 /aaai/2020/kumar2020aaai-task/

Abstract

We propose an abstraction method for open-world environments expressed as Factored Markov Decision Processes (FMDPs) with very large state and action spaces. Our method prunes state and action variables that are irrelevant to the optimal value function on the state subspace the agent would visit when following any optimal policy from the initial state. This method thus enables tractable fast planning within large open-world FMDPs.

PDF AAAI Semantic Scholar

Cite

Text

Kumar et al. "Task Scoping for Efficient Planning in Open Worlds (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020. doi:10.1609/AAAI.V34I10.7195

Markdown

[Kumar et al. "Task Scoping for Efficient Planning in Open Worlds (Student Abstract)." AAAI Conference on Artificial Intelligence, 2020.](https://mlanthology.org/aaai/2020/kumar2020aaai-task/) doi:10.1609/AAAI.V34I10.7195

BibTeX

@inproceedings{kumar2020aaai-task,
  title     = {{Task Scoping for Efficient Planning in Open Worlds (Student Abstract)}},
  author    = {Kumar, Nishanth and Fishman, Michael and Danas, Natasha and Tellex, Stefanie and Littman, Michael and Konidaris, George},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2020},
  pages     = {13845-13846},
  doi       = {10.1609/AAAI.V34I10.7195},
  url       = {https://mlanthology.org/aaai/2020/kumar2020aaai-task/}
}