Provably Efficient Model-Free Constrained RL with Linear Function Approximation

Authors: Arnob Ghosh, Xingyu Zhou, Ness Shroff

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate Algorithm 1 on a simulated model for job scheduling to validate our theoretical results.
Researcher Affiliation Academia Arnob Ghosh Electrical and Computer Engineering The Ohio State University Columbus, OH, USA ghosh.244@osu.edu Xingyu Zhou Electrical and Computer Engineering Wayne State University Detroit, MI, USA xingyu.zhou@wayne.edu Ness Shroff Electrical and Computer Engineering The Ohio State University Columbus, OH, USA shroff.11@osu.edu
Pseudocode Yes Algorithm 1 Model Free Primal-Dual Algorithm for Linear Function Approximation
Open Source Code No The paper states in a checklist that code is included, but does not provide a URL or explicit mention within the main body of the text for public access.
Open Datasets No The paper uses a 'simulated model for job scheduling' and does not provide concrete access information or citations for a publicly available dataset.
Dataset Splits No The paper uses a simulated model for experiments and does not specify any train/validation/test dataset splits or their methodology.
Hardware Specification No The paper does not provide any specific hardware details for running the experiments, and the authors state 'N/A' for compute resources in the checklist.
Software Dependencies No The paper does not list specific software dependencies with version numbers.
Experiment Setup Yes The parameters we used are the followings: α = K/(1 + 2H/γ + H), η = 2H/(γ KH2). We set γ = 1. We have also set ϵ = 0.1 in order to ensure that the violation goes towards 0 as K increases.