Proceedings

Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search

Download BibTeX Cite

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence. Main track. Pages 5562-5568.

https://doi.org/10.24963/ijcai.2019/772

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.

Thomas Gabor, Jan Peter, Thomy Phan, Christian Meyer, and Claudia Linnhoff-Popien. 2019. Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19. IJCAI, 5562–5568. https://doi.org/10.24963/ijcai.2019/772
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards