Information-Theoretic Considerations in Batch Reinforcement Learning

Authors: Jinglin Chen, Nan Jiang

ICML 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper, we revisit these assumptions and provide theoretical results towards answering the above questions, and make steps towards a deeper understanding of value-function approximation.
Researcher Affiliation Academia 1University of Illinois at Urbana-Champaign, Urbana, Illinois, USA.
Pseudocode No The paper describes algorithms such as Fitted Q-Iteration (FQI) conceptually (
Open Source Code No The paper does not mention providing open-source code for the described methodology.
Open Datasets No The paper is theoretical and describes general batch datasets (
Dataset Splits No The paper is theoretical and does not perform experiments with specific dataset splits.
Hardware Specification No The paper is theoretical and does not discuss hardware specifications for experiments.
Software Dependencies No The paper is theoretical and does not specify any software dependencies or versions.
Experiment Setup No The paper is theoretical and does not describe a specific experimental setup, hyperparameters, or training configurations.