Regular Decision Processes: A Model for Non-Markovian Domains

Authors: Ronen I. Brafman, Giuseppe De Giacomo

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We introduce and study Regular Decision Processes (RDPs), a new, compact, factored model for domains with non-Markovian dynamics and rewards. ... The main contributions of this paper are to introduce RDPs, study their properties and complexity, describe how to optimize them, and postulate a potential method for learning them from observations.
Researcher Affiliation Academia 1Ben-Gurion University, Israel 2Sapienza Universit a di Roma, Italy brafman@cs.bgu.ac.il, degiacomo@dis.uniroma1.it
Pseudocode Yes Algorithm 1 Pseudocode for Learning Finite NMDPs
Open Source Code No The paper mentions automated tools for constructing DFAs (e.g., https://flloat.herokuapp.com [Favorito, 2018] http://ltlf2dfa.diag.uniroma1.it [Fuggitti, 2018]) but does not provide a link or explicit statement about the availability of source code for the methodology described in this paper.
Open Datasets No The paper is theoretical and does not mention using any dataset for training. No information about publicly available datasets or their access is provided.
Dataset Splits No The paper is theoretical and does not mention any dataset splits (training, validation, or test). Therefore, no specific dataset split information is provided.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running experiments, as it is a theoretical work.
Software Dependencies No The paper mentions external tools (e.g., float.herokuapp.com, ltlf2dfa.diag.uniroma1.it) but does not provide specific version numbers for these or any other ancillary software dependencies used in their own work.
Experiment Setup No The paper is theoretical and does not describe any experimental setup details, hyperparameters, or training configurations.