Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. Main track. Pages 5562-5568.
https://doi.org/10.24963/ijcai.2019/772
Keywords
- Planning and Scheduling: Temporal and Hybrid planning
- Planning and Scheduling: Planning Algorithms
- Planning and Scheduling: Hierarchical planning
Abstract
We propose an approach to general subgoal-based temporal abstraction in MCTS. Our approach approximates a set of available macro-actions locally for each state only requiring a generative model and a subgoal predicate. For that, we modify the expansion step of MCTS to automatically discover and optimize macro-actions that lead to subgoals. We empirically evaluate the effectiveness, computational efficiency and robustness of our approach w.r.t. different parameter settings in two benchmark domains and compare the results to standard MCTS without temporal abstraction.
@inproceedings{ijcai2019p772,
title = {Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search},
author = {Gabor, Thomas and Peter, Jan and Phan, Thomy and Meyer, Christian and Linnhoff-Popien, Claudia},
booktitle = {Proceedings of the Twenty-Eighth International Joint Conference on
Artificial Intelligence, {IJCAI-19}},
publisher = {International Joint Conferences on Artificial Intelligence Organization},
editor = {Sarit Kraus},
pages = {5562--5568},
year = {2019},
month = {8},
note = {Main track},
doi = {10.24963/ijcai.2019/772},
url = {https://doi.org/10.24963/ijcai.2019/772},
}
TY - CPAPER TI - Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search AU - Gabor, Thomas AU - Peter, Jan AU - Phan, Thomy AU - Meyer, Christian AU - Linnhoff-Popien, Claudia T2 - Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19 PB - International Joint Conferences on Artificial Intelligence Organization PY - 2019 SP - 5562 EP - 5568 DO - 10.24963/ijcai.2019/772 UR - https://doi.org/10.24963/ijcai.2019/772 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: