Interaction-Grounded Learning

Authors: Tengyang Xie, John Langford, Paul Mineiro, Ida Momennejad

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

Reproducibility Variable Result LLM Response
Research Type Experimental In this section, we provide empirical evaluations in simulated environments. We experiment with both batch and online IGL.
Researcher Affiliation Collaboration Tengyang Xie 1 John Langford 2 Paul Mineiro 2 Ida Momennejad 2 1University of Illinois at Urbana-Champaign 2Microsoft Research, New York City.
Pseudocode Yes Algorithm 1 E2G
Open Source Code No The paper does not contain an explicit statement about releasing source code, nor does it provide a link to a code repository.
Open Datasets Yes We evaluated our approach on the MNIST environment based on the infinite MNIST simulator (Loosli et al., 2007).
Dataset Splits No The paper states: 'Over our experiments in the batch mode, we use the uniform policy πbad to gather data, and the number of examples is 60000.' It does not specify train, validation, or test splits for this dataset.
Hardware Specification No The paper does not provide any specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions 'logistic regression' and 'softmax policies' but does not specify any software names with version numbers for reproducibility (e.g., specific libraries or frameworks like PyTorch 1.9 or TensorFlow 2.x).
Experiment Setup No The paper states: 'We provide the details on setting up the experiments in Appendix B', but Appendix B is not included in the provided text, hence no specific experimental setup details are present in the main body.