Spremljaj
Masataro Asai
Masataro Asai
Research Staff Member, IBM Research, MIT-IBM Watson AI Lab
Preverjeni e-poštni naslov na ibm.com - Domača stran
Naslov
Navedeno
Navedeno
Leto
Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary
M Asai, A Fukunaga
AAAI, 6094-6101, 2018
2262018
Unsupervised Grounding of Plannable First-Order Logic Representation from Images
M Asai
Twenty-Ninth International Conference on Automated Planning and Scheduling …, 2019
752019
Learning Neural-Symbolic Descriptive Planning Models via Cube-Space Priors: The Voyage Home (to STRIPS)
M Asai, C Muise
IJCAI, 2020
732020
Reinforcement learning for classical planning: Viewing heuristics as dense reward generators
C Gehring, M Asai, R Chitnis, T Silver, L Kaelbling, S Sohrabi, M Katz
Proceedings of the International Conference on Automated Planning and …, 2022
472022
Tie-breaking strategies for cost-optimal best first search
M Asai, A Fukunaga
Journal of Artificial Intelligence Research 58, 67-121, 2017
292017
Solving large-scale planning problems by decomposition and macro generation
M Asai, A Fukunaga
Proceedings of the International Conference on Automated Planning and …, 2015
272015
Tiebreaking strategies for A* search: How to explore the final frontier
M Asai, A Fukunaga
AAAI, 673--679, 2016
26*2016
Classical planning in deep latent space
M Asai, H Kajino, A Fukunaga, C Muise
Journal of Artificial Intelligence Research 74, 1599-1686, 2022
252022
Towards Stable Symbol Grounding with Zero-Suppressed State AutoEncoder
M Asai, H Kajino
Twenty-Ninth International Conference on Automated Planning and Scheduling …, 2019
202019
Exploration among and within plateaus in greedy best-first search
M Asai, A Fukunaga
Proceedings of the International Conference on Automated Planning and …, 2017
192017
Photo-realistic blocksworld dataset
M Asai
arXiv preprint arXiv:1812.01818, 2018
132018
Fully automated cyclic planning for large-scale manufacturing domains
M Asai, A Fukunaga
Proceedings of the International Conference on Automated Planning and …, 2014
122014
Unsuccessful Neural-Symbolic Descriptive Action Model from Images: The Search for STRIPS
M Asai
ICAPS Workshop on Knowledge Engineering for Planning and Scheduling (KEPS), 2020
8*2020
Scale-Adaptive Balancing of Exploration and Exploitation in Classical Planning
S Wissow, M Asai
ECAI 2024, 4216-4223, 2024
42024
Discrete word embedding for logical natural language understanding
M Asai, Z Tang
arXiv preprint arXiv:2008.11649, 2020
42020
Discovering higher-level actions from expert's action demonstration
M Tatsubori, RE Fall III, DJR Agravante, M Asai, A Munawar
US Patent 11,526,729, 2022
32022
On Using Admissible Bounds for Learning Forward Search Heuristics
C Núñez-Molina, M Asai, J Fernandez-Olivares, P Mesejo
IJCAI, 2024
22024
Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari
B Ayton, M Asai
Proceedings of the International Conference on Automated Planning and …, 2022
2*2022
Permutation-invariant optimization metrics for neural networks
M Asai
US Patent App. 16/366,678, 2020
22020
Symbolic model training with active learning
A Kishimoto, M Asai, HOU Yufang, H Kajino, R Marinescu
US Patent 12,165,019, 2024
12024
Sistem trenutno ne more izvesti postopka. Poskusite znova pozneje.
Članki 1–20