Batch Value-function Approximation with Only Realizability

Authors: Tengyang Xie, Nan Jiang

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Our algorithm, BVFT, breaks the hardness conjecture (albeit under a stronger notion of exploratory data) via a tournament procedure that reduces the learning problem to pairwise comparison, and solves the latter with the help of a state-action-space partition constructed from the compared functions. We present the algorithm in Section 4 and prove its sample complexity in Sections 5 and 6.
Researcher Affiliation Academia 1Department of Computer Science, University of Illinois at Urbana-Champaign, Illinois, USA. Correspondence to: Nan Jiang <nanjiang@illinois.edu>.
Pseudocode Yes Algorithm 1 Batch Value-Function Tournament (BVFT)
Open Source Code No The paper does not contain any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets No The paper assumes access to a "batch dataset D" for theoretical analysis but does not specify a real-world, publicly available dataset with concrete access information.
Dataset Splits No The paper is theoretical and does not involve empirical experiments with datasets, thus it does not provide information about dataset splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not present empirical experiments, thus it does not specify any hardware used for running experiments.
Software Dependencies No The paper is theoretical and does not present empirical experiments, thus it does not list any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not present empirical experiments, thus it does not provide details about experimental setup, such as hyperparameter values or training configurations.