Provable Interactive Learning with Hindsight Instruction Feedback

Authors: Dipendra Misra, Aldo Pacchiano, Robert E. Schapire

ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We provide experiments showing the performance of LORIL in practice for 2 domains.
Researcher Affiliation Collaboration 1Microsoft Research 2Broad Institute of MIT and Harvard, Boston University.
Pseudocode Yes Algorithm 1 LORIL(g , F): Learning in LOw-Rank models from Instruction Labels
Open Source Code Yes The code for all experiments in the paper can be found at https://github. com/microsoft/Intrepid.
Open Datasets No The paper mentions evaluating on a 'synthetic task' and an 'image selection task' but does not provide specific access information (link, DOI, citation) for a publicly available or open dataset.
Dataset Splits No The paper provides details on hyperparameters and model architecture but does not specify training, validation, or test dataset splits (e.g., percentages or sample counts).
Hardware Specification Yes We use A2600 for all experiments.
Software Dependencies No The paper mentions 'Py Torch' but does not specify a version number or other software dependencies with their versions.
Experiment Setup Yes We select hyperparameters for each algorithm based on the mean final regret. We tune the hyperparameters λ and C for LORIL and ϵ for ϵ-greedy using grid search.