Efficient Performance Bounds for Primal-Dual Reinforcement Learning from Demonstrations

Authors: Angeliki Kamoutsi, Goran Banjac, John Lygeros

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

Reproducibility Variable Result LLM Response
Research Type Experimental We further present an equivalent no-regret online-learning interpretation.In Appendix E we provide preliminary empirical results on a simple tabular MDP in order to illustrate our formulations and theoretical results.
Researcher Affiliation Academia 1Automatic Control Laboratory, ETH Zurich, Switzerland. Correspondence to: Angeliki Kamoutsi <kamoutsa@ethz.ch>.
Pseudocode Yes Algorithm 1 Stochastic Primal-Dual Lf D
Open Source Code No The paper does not contain an explicit statement about providing open-source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets No The paper mentions using 'a finite set of expert demonstrations' and conducting 'preliminary empirical results on a simple tabular MDP' but does not provide specific access information (link, DOI, formal citation) for any publicly available dataset.
Dataset Splits No The paper does not specify exact percentages or sample counts for training, validation, or test splits, nor does it reference predefined splits with citations.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU/GPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies, libraries, or solver names with their version numbers needed for replication.
Experiment Setup Yes Input: number of iterations N, step-size η, radius β and Set θ1,i = 1 nµ , i [nµ], w1,i = 1 nc , i [nc], λ = 0 and learning rate η = 1 γ β Nnµ .