Optimistic Planning by Regularized Dynamic Programming

Authors: Antoine Moulin, Gergely Neu

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We propose a new method for optimistic planning in infinite-horizon discounted Markov decision processes... We use our method to recover known guarantees in tabular MDPs and to provide a computationally efficient algorithm for learning near-optimal policies in discounted linear mixture MDPs from a single stream of experience, and show it achieves near-optimal statistical guarantees.
Researcher Affiliation Academia 1Universitat Pompeu Fabra, Barcelona, Spain. Correspondence to: Antoine Moulin <antoine.moulin@upf.edu>, Gergely Neu <gergely.neu@gmail.com>.
Pseudocode Yes The overall procedure is presented as Algorithm 1. ... Algorithm 2 RAVI-UCB for tabular MDPs. ... Algorithm 3 RAVI-UCB for linear mixture MDPs.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is openly available.
Open Datasets No The paper is theoretical and does not conduct experiments involving datasets or their public availability. The term 'train' is not used in the context of empirical data training.
Dataset Splits No The paper is theoretical and does not conduct experiments with dataset splits. The term 'validation' is used once in 'validation of existing assumptions' which is not related to data splitting.
Hardware Specification No The paper is theoretical and does not describe empirical experiments, therefore no hardware specifications are mentioned.
Software Dependencies No The paper is theoretical and does not describe empirical experiments, therefore no specific software dependencies with version numbers are mentioned.
Experiment Setup No The paper is theoretical and does not describe empirical experiments with specific hyperparameter values or training configurations. The 'setup' discussed refers to the theoretical model setup.