Improving PAC Exploration Using the Median Of Means

Authors: Jason Pazis, Ronald E. Parr, Jonathan P. How

NeurIPS 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We compared Median-PAC against the algorithm of Pazis and Parr [12] on a simple 5 by 5 gridworld (see appendix for more details).
Researcher Affiliation Academia Jason Pazis Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge, MA 02139, USA jpazis@mit.edu Ronald Parr Department of Computer Science Duke University Durham, NC 27708 parr@cs.duke.edu Jonathan P. How Aerospace Controls Laboratory Department of Aeronautics and Astronautics Massachusetts Institute of Technology Cambridge, MA 02139, USA jhow@mit.edu
Pseudocode Yes Algorithm 1 Median-PAC
Open Source Code No The paper does not provide concrete access to source code (specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described in this paper.
Open Datasets No The experiments are conducted in a 'simple 5 by 5 gridworld' which describes the environment, not a publicly available dataset. There is no information about accessing a pre-existing dataset.
Dataset Splits No The paper describes experiments in a 'simple 5 by 5 gridworld' environment, which is an interaction-based setup, and does not mention any training, validation, or test dataset splits.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No While the paper describes the environment and the algorithm's inputs (parameters k, km, a), it does not provide specific numerical values for hyperparameters or training settings within the main text or the provided abstract/introduction/experimental section.