Temporally Abstract Partial Models

Authors: Khimya Khetarpal, Zafarali Ahmed, Gheorghe Comanici, Doina Precup

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

Reproducibility Variable Result LLM Response
Research Type Experimental Additionally, we empirically demonstrate the ability to learn both affordances and partial option models online resulting in improved sample efficiency and planning time in the Taxi domain.Empirically, we demonstrate end-to-end learning of affordances and partial option models, showcasing significant improvement in final performance and sample efficiency when used for planning in the Taxi domain (Sec. 5).
Researcher Affiliation Collaboration Khimya Khetarpal 1,2, Zafarali Ahmed 3, Gheorghe Comanici 3, Doina Precup1,2,3 1Mc Gill University, 2Mila, 3Deep Mind
Pseudocode Yes Affordances can be incorporated into planning by only considering state-option pairs in the affordance set (See Algorithm 1 in the Appendix).
Open Source Code No The paper states in a footnote: 'We will provide the source code for our empirical analysis here.' However, no active link or specific repository information is provided within the paper.
Open Datasets Yes Environment. We consider the 5x5 Taxi domain (Dietterich, 2000).
Dataset Splits No The paper mentions 'train', 'validation', and 'test' in the context of data for experiments, but it does not provide specific details on how the dataset was split (e.g., percentages, sample counts, or specific predefined splits with citations).
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments (e.g., GPU/CPU models, memory).
Software Dependencies No The paper mentions using the 'Launchpad framework (Yang et al., 2021)' but does not provide specific version numbers for any software dependencies.
Experiment Setup No The paper describes the general experimental pipeline, including data collection and model learning processes, but it does not provide specific hyperparameter values or detailed training configurations (e.g., learning rates, batch sizes, optimizer settings) in the main text.