Learning Abstract Options

Authors: Matthew Riemer, Miao Liu, Gerald Tesauro

NeurIPS 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our empirical results in both discrete and continuous environments demonstrate the efficiency of our framework.
Researcher Affiliation Industry Matthew Riemer, Miao Liu, and Gerald Tesauro IBM Research T.J. Watson Research Center, Yorktown Heights, NY {mdriemer, miao.liu1, gtesauro}@us.ibm.com
Pseudocode No The paper states: "We include detailed algorithm descriptions for all of our experiments in Appendix 2." However, it does not explicitly contain a clearly labeled "Pseudocode" or "Algorithm" block in the main text, and the content of Appendix 2 is not provided to verify.
Open Source Code No The paper does not provide any specific repository link, explicit code release statement, or mention of code in supplementary materials for the methodology described.
Open Datasets Yes We first consider a navigation task in the four-rooms domain [29]. ... We finally consider application of the HOC to the Atari games [2].
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, and test sets. It mentions evaluating policies over certain episodes but not explicit data splits.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions using A3C and various network components (convolutional network, LSTM) but does not provide specific ancillary software details with version numbers (e.g., library or solver names with version numbers like Python 3.8, PyTorch 1.9, TensorFlow 2.x).
Experiment Setup Yes We include detailed algorithm descriptions for all of our experiments in Appendix 2. We also conducted hyperparameter optimization that is summarized along with detail on experimental protocol in Appendix 2.