Computationally Efficient Horizon-Free Reinforcement Learning for Linear Mixture MDPs

Authors: Dongruo Zhou, Quanquan Gu

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

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct some numerical experiments to suggest the validity of HF-UCRL-VTR+ in Appendix A.
Researcher Affiliation Academia Dongruo Zhou Department of Computer Science University of California, Los Angeles Los Angeles, CA 90095 drzhou@cs.ucla.edu Quanquan Gu Department of Computer Science University of California, Los Angeles Los Angeles, CA 90095 qgu@cs.ucla.edu
Pseudocode Yes Algorithm 1 Weighted OFUL+ Algorithm 2 HF-UCRL-VTR+ Algorithm 3 High-order moment estimator (HOME)
Open Source Code No Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [N/A]
Open Datasets No The paper does not specify the use of any publicly available datasets or provide access information for data used in numerical experiments.
Dataset Splits No The paper does not provide explicit training, validation, or test dataset splits. The ethics review section states: "Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]"
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. The ethics review section states: "Did you include the total amount of compute and the type of resources used (e.g., type of GPUs, internal cluster, or cloud provider)? [N/A]"
Software Dependencies No The paper does not provide specific software dependencies with version numbers needed to replicate the experiment. The ethics review section states: "Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]"
Experiment Setup No The paper states that for numerical experiments "the parameter B in the MDP is 1, d = 4... the regularization parameter λ = 0.01 and α = 0.001." However, it does not provide comprehensive training hyperparameters such as learning rate, batch size, or optimizer settings. The ethics review section states: "Did you specify all the training details (e.g., data splits, hyperparameters, how they were chosen)? [N/A]"