Task Scoping for Efficient Planning in OpenWorlds
Publication
, Conference
Kumar, N; Fishman, M; Danas, N; Tellex, S; Littman, M; Konidaris, G
Published in: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
January 1, 2020
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.
Duke Scholars
Published In
AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
ISBN
9781577358350
Publication Date
January 1, 2020
Start / End Page
13845 / 13846
Citation
APA
Chicago
ICMJE
MLA
NLM
Kumar, N., Fishman, M., Danas, N., Tellex, S., Littman, M., & Konidaris, G. (2020). Task Scoping for Efficient Planning in OpenWorlds. In AAAI 2020 - 34th AAAI Conference on Artificial Intelligence (pp. 13845–13846).
Kumar, N., M. Fishman, N. Danas, S. Tellex, M. Littman, and G. Konidaris. “Task Scoping for Efficient Planning in OpenWorlds.” In AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, 13845–46, 2020.
Kumar N, Fishman M, Danas N, Tellex S, Littman M, Konidaris G. Task Scoping for Efficient Planning in OpenWorlds. In: AAAI 2020 - 34th AAAI Conference on Artificial Intelligence. 2020. p. 13845–6.
Kumar, N., et al. “Task Scoping for Efficient Planning in OpenWorlds.” AAAI 2020 - 34th AAAI Conference on Artificial Intelligence, 2020, pp. 13845–46.
Kumar N, Fishman M, Danas N, Tellex S, Littman M, Konidaris G. Task Scoping for Efficient Planning in OpenWorlds. AAAI 2020 - 34th AAAI Conference on Artificial Intelligence. 2020. p. 13845–13846.
Published In
AAAI 2020 - 34th AAAI Conference on Artificial Intelligence
ISBN
9781577358350
Publication Date
January 1, 2020
Start / End Page
13845 / 13846