POMDPs in Continuous Time and Discrete Spaces

Authors: Bastian Alt, Matthias Schultheis, Heinz Koeppl

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

Reproducibility Variable Result LLM Response
Research Type Experimental We show the applicability on a set of toy examples which pave the way for future methods providing solutions for high dimensional problems.
Researcher Affiliation Academia Technische Universität Darmstadt {bastian.alt, matthias.schultheis, heinz.koeppl}@bcs.tu-darmstadt.de
Pseudocode No The paper refers to algorithms but does not contain a clearly labeled pseudocode or algorithm block within the provided text.
Open Source Code Yes An implementation of our proposed method is publicly available1. 1https://git.rwth-aachen.de/bcs/pomdps_continuous_time_discrete_spaces
Open Datasets No The paper uses adapted 'toy examples' and describes problem setups rather than relying on and providing access information for a public, pre-existing dataset.
Dataset Splits No The paper describes learning on simulated trajectories and does not mention specific train/validation/test dataset splits with percentages or counts for reproducibility.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions using deep learning techniques but does not provide specific software dependencies or their version numbers required to replicate the experiment.
Experiment Setup No The paper describes the experimental tasks and learning algorithms but does not provide specific details such as hyperparameter values, batch sizes, learning rates, or optimizer settings for the neural networks used in the experiments.