Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
- Clement Gehring
- Masataro Asai
- et al.
- 2022
- ICAPS 2022
Publications
This is our catalog of publications authored by IBM researchers, in collaboration with the global research community. It’s an ever-growing body of work that shows why IBM is one of the most important contributors to modern computing.
Date
Featured collections
Popular topics
6 results for Masataro Asai
Learning neural-symbolic descriptive planning models via cube-space priors: The voyage home (to STRIPS)
- Masataro Asai
- Christian Muise
- 2021
- IJCAI 2020
Unsupervised grounding of plannable first-order logic representation from images
- Masataro Asai
- 2019
- ICAPS 2019
Towards stable symbol grounding with zero-suppressed State AutoEncoder
- Masataro Asai
- Hiroshi Kajino
- 2019
- ICAPS 2019
Efficient optimal search under expensive edge cost computation
- Masataro Asai
- Akihiro Kishimoto
- et al.
- 2017
- IJCAI 2017
Classical Planning in Deep Latent Space
- Masataro Asai
- Hiroshi Kajino
- et al.
- 2022
- JAIR