Improving Sample Complexity Bounds for (Natural) Actor-Critic Algorithms

Authors: Tengyu Xu, Zhe Wang, Yingbin Liang

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical This is the first theoretical study establishing that AC and NAC attain orderwise performance improvement over PG and NPG under infinite horizon due to the incorporation of critic.
Researcher Affiliation Academia Department of ECE, The Ohio State University
Pseudocode Yes Algorithm 1 Actor-critic (AC) and natural actor-critic (NAC) online algorithms; Algorithm 2 Minibatch-TD(sini, π, φ, β, Tc, M)
Open Source Code No The paper does not provide any explicit statements about releasing source code for the described methodology or links to a code repository.
Open Datasets No The paper is theoretical and does not conduct empirical experiments on a specific dataset; thus, it does not describe any training dataset or its availability.
Dataset Splits No The paper is theoretical and does not report on empirical experiments; thus, it does not specify any dataset splits for training, validation, or testing.
Hardware Specification No The paper is a theoretical study and does not report on empirical experiments; therefore, it does not specify any hardware used.
Software Dependencies No The paper is a theoretical study and does not report on empirical experiments; therefore, it does not specify any software dependencies with version numbers for replication.
Experiment Setup No The paper describes algorithms with general parameters like 'actor stepsize α, critic stepsize β, regularization λ' but does not provide specific hyperparameter values or system-level training settings for an empirical experimental setup.