Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

Authors: Shenao Zhang, Boyi Liu, Zhaoran Wang, Tuo Zhao

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experimental results demonstrate that proper normalization significantly reduces the gradient variance of model-based RP PGMs. As a result, the performance of the proposed method is comparable or superior to other gradient estimators, such as the Likelihood Ratio (LR) gradient estimator. Our code is available at https://github.com/agentification/RP_PGM.
Researcher Affiliation Academia 1Northwestern University 2Georgia Tech
Pseudocode Yes Algorithm 1 Model-Based Reparameterization Policy Gradient
Open Source Code Yes Our code is available at https://github.com/agentification/RP_PGM.
Open Datasets No The paper refers to "Mu Jo Co [57] tasks" as the environment for experiments, but does not provide concrete access information (link, DOI, formal citation with authors/year, or specific dataset name) for a publicly available dataset used for training.
Dataset Splits No The paper does not specify exact percentages, sample counts, or refer to predefined splits for training, validation, or test datasets.
Hardware Specification No The paper does not provide specific hardware details such as exact GPU/CPU models, processor types, or memory amounts used for running experiments.
Software Dependencies No The paper mentions using "Py Torch [44]" but does not provide a specific version number for this or any other software dependency.
Experiment Setup No The paper describes network architectures and algorithm choices, but does not provide specific hyperparameters like learning rate, batch size, or number of epochs for the experimental setup.