Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search

Authors: Thomas Gabor, Jan Peter, Thomy Phan, Christian Meyer, Claudia Linnhoff-Popien

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 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.
Researcher Affiliation Academia LMU Munich thomas.gabor@ifi.lmu.de
Pseudocode Yes Algorithm 1 Expansion with Macro-Action Generation
Open Source Code Yes The code can be found at github.com/jnptr/subgoal-mcts.
Open Datasets Yes Gridworld is one of the must studied example domains in artificial intelligence [Sutton et al., 1999; Russell and Norvig, 2010; Bai et al., 2016; Sutton and Barto, 2018]. The Tetris game is another popular research domain in artificial intelligence research [Thiery and Scherrer, 2009; Zhongjie et al., 2011; Scherrer et al., 2015; Jaskowski et al., 2015].
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, and test sets, as the research focuses on online planning in simulation environments rather than traditional dataset-based model training.
Hardware Specification No The paper mentions using multithreading and multiple cores, but does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running experiments.
Software Dependencies No The paper does not provide specific software dependency details, such as library names with version numbers, beyond general algorithmic components like UCB1.
Experiment Setup Yes For all experiments, we set γ = 1, p0 = 0.95, and α = 0.001. For all parameter configurations, see github.com/hugo-voodo/temporal-abstraction/blob/master/supplement.pdf.