reproducibilityindex.ai

Sample-Efficient Constrained Reinforcement Learning with General Parameterization

Authors: Washim Mondal, Vaneet Aggarwal

Reproducibility Variable	Result	LLM Response
Research Type	Theoretical	Our paper is primarily of theoretical nature and does not include experiments.
Researcher Affiliation	Academia	Washim Uddin Mondal Department of Electrical Engineering Indian Institute of Technology Kanpur Kanpur, UP, India 208016 wmondal@iitk.ac.in Vaneet Aggarwal School of IE and ECE Purdue University West Lafayette, IN, USA 47906 vaneet@purdue.edu
Pseudocode	Yes	Algorithm 1 Unbiased Sampling and Algorithm 2 Primal-Dual Accelerated Natural Policy Gradient (PD-ANPG) are provided in the paper.
Open Source Code	No	Our paper is primarily of theoretical nature and does not include experiments.
Open Datasets	No	Our paper is primarily of theoretical nature and does not include experiments.
Dataset Splits	No	Our paper is primarily of theoretical nature and does not include experiments.
Hardware Specification	No	Our paper is primarily of theoretical nature and does not include experiments.
Software Dependencies	No	Our paper is primarily of theoretical nature and does not include experiments.
Experiment Setup	No	Our paper is primarily of theoretical nature and does not include experiments.