Learning Plannable Representations with Causal InfoGAN

Authors: Thanard Kurutach, Aviv Tamar, Ge Yang, Stuart J. Russell, Pieter Abbeel

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

Reproducibility Variable Result LLM Response
Research Type Experimental We begin our investigation with a set of toy tasks, specifically designed to demonstrate the benefits of CIGAN, where we can also perform an extensive quantitative evaluation. We later present experiments on a real dataset of robotic rope manipulation.
Researcher Affiliation Academia 1Berkeley AI Research, University of California, Berkeley 2Department of Physics, University of Chicago
Pseudocode No The paper mentions "we provide a detailed algorithm in Appendix C," but no pseudocode or algorithm blocks are present in the main body of the paper.
Open Source Code Yes Code is available online at http://github.com/thanard/causal-infogan.
Open Datasets Yes We later present experiments on a real image data collected by Nair et al. [29] of a robot randomly poking a rope. ... We train a CIGAN model on the rope manipulation data of [29].
Dataset Splits No The paper states: "We chose algorithm parameters and stopping criteria by measuring the average feasibility score on a validation set of start/goal observations", but it does not specify the size, percentages, or method for creating this validation set split from the full dataset.
Hardware Specification No The paper does not provide any specific hardware details such as GPU models, CPU models, or memory specifications used for running the experiments.
Software Dependencies No The paper does not provide specific software dependency details with version numbers (e.g., programming languages, libraries, frameworks, or solvers).
Experiment Setup No The paper describes the models and general experimental procedure but does not provide concrete hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) or system-level training configurations in the main text.