Learning and Solving Regular Decision Processes

Authors: Eden Abadi, Ronen I. Brafman

IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically evaluate this approach, demonstrating its feasibility.
Researcher Affiliation Academia Eden Abadi and Ronen I. Brafman Department of Computer Science, Ben Gurion University, Israel abadied@post.bgu.ac.il, brafman@cs.bgu.ac.il
Pseudocode Yes The high-level pseudo-code of our algorithm, S3M (Sample, Merge, Mealy Machine), is given in Algorithm 1.
Open Source Code No The paper does not provide an explicit statement or link to its source code.
Open Datasets No The paper introduces "two new RDP domains: NM-MAB and Rotating Maze" which are custom domains and does not provide concrete access information (link, DOI, formal citation) for publicly available datasets.
Dataset Splits No The paper does not provide specific dataset split information (e.g., percentages, sample counts) for training, validation, or test sets, nor does it refer to predefined splits with citations or detailed splitting methodology.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions using "EDSM implementation from the Flex Fringe library" and "UCT" but does not provide specific version numbers for these software components.
Experiment Setup No The paper mentions parameters like 'c' for UCB1, 'α' and 'ϵ' for Q-learning, 'min samples', 'ϵ' for KL divergence merging, and 'λ' for the loss function, but does not provide their specific numerical values.