Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].

MetaCURL: Non-stationary Concave Utility Reinforcement Learning

Authors: Bianca Marin Moreno, Margaux Brégère, Pierre Gaillard, Nadia Oudjane

NeurIPS 2024 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Justification: This is a theoretical paper, with no experiments.
Researcher Affiliation Collaboration Bianca Marin Moreno Inria Margaux Brégère Sorbonne Université Pierre Gaillard Inria Nadia Oudjane EDF R&D
Pseudocode Yes Algorithm 1 Meta CURL with EWA... Algorithm 2 EWA (Exponentially Weighted Average)... Algorithm 3 Online estimation of the probability kernel (ˆpt estimator)... Algorithm 4 Greedy MD-CURL
Open Source Code No Justification: This is a theoretical paper, with no experiments. The NeurIPS checklist states 'This paper does not release new assets.' and 'The answer NA means that the paper does not include experiments.'
Open Datasets No Justification: This is a theoretical paper, with no experiments or datasets. The NeurIPS checklist states 'The answer NA means that the paper does not include experiments.'
Dataset Splits No Justification: This is a theoretical paper, with no experiments or datasets. The NeurIPS checklist states 'The answer NA means that the paper does not include experiments.'
Hardware Specification No Justification: This is a theoretical paper, with no experiments. The NeurIPS checklist states 'The answer NA means that the paper does not include experiments.'
Software Dependencies No Justification: This is a theoretical paper, with no experiments. The NeurIPS checklist states 'The answer NA means that the paper does not include experiments.'
Experiment Setup No Justification: This is a theoretical paper, with no experiments. The NeurIPS checklist states 'The answer NA means that the paper does not include experiments.'