Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search Article Swipe

PDF

Related Concepts

Computer science Predicate abstraction Abstraction Robustness (evolution) Theoretical computer science Artificial intelligence Predicate (mathematical logic) Benchmark (surveying) Macro Generative model Machine learning Generative grammar Algorithm Model checking Programming language Philosophy Gene Chemistry Epistemology Geodesy Biochemistry Geography

Thomas Gabor , J. Hencil Peter , Thomy Phan , Christian Meyer , Claudia Linnhoff‐Popien ·

YOU? · · 2019 · Open Access · · DOI: https://doi.org/10.24963/ijcai.2019/772 · OA: W2965360642

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.