Unveiling Options with Neural Network Decomposition

Authors: Mahdi Alikhasi, Levi Lelis

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results in two grid-world domains where exploration can be difficult confirm that our method can identify useful options, thereby accelerating the learning process on similar but different tasks.
Researcher Affiliation Academia Mahdi Alikhasi and Levi H. S. Lelis Amii, Department of Computing Science, University of Alberta {alikhasi,levi.lelis}@ualberta.ca
Pseudocode Yes Algorithm 1 COMPUTE-LOSS
Open Source Code Yes The implementation used in our experiments is available online.1 1https://github.com/lelis-research/Dec-Options
Open Datasets Yes Mini Grid (Chevalier-Boisvert et al., 2023)
Dataset Splits No The paper mentions using training and validation sets but does not provide specific details on the split percentages or how the data is partitioned for these sets.
Hardware Specification No The paper mentions support from 'Digital Research Alliance of Canada' but does not provide specific hardware details such as GPU or CPU models used for the experiments.
Software Dependencies No The paper mentions using 'Stable-baselines framework (Raffin et al., 2021)' but does not provide specific version numbers for this or other software dependencies.
Experiment Setup Yes Additional details, including agent architectures, hyperparameter settings, and used libraries are provided in the Appendix.