Unsupervised Learning of Object Keypoints for Perception and Control

Authors: Tejas D. Kulkarni, Ankush Gupta, Catalin Ionescu, Sebastian Borgeaud, Malcolm Reynolds, Andrew Zisserman, Volodymyr Mnih

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In section 4.1 we first evaluate the long-term tracking ability of our object keypoint detector. Next, in section 4.2 we evaluate the application of the keypoint detector on two control tasks comparison against state-of-the-art model-based and model-free methods for data-efficient learning on Atari ALE games [1] in section 4.2.1, and in section 4.2.2 examine efficient exploration by learning to control the discovered keypoints; we demonstrate reaching states otherwise unreachable through random explorations on raw-actions, and also recover the agent self as the most-controllable keypoint. For implementation details, please refer to the supplementary material.
Researcher Affiliation Collaboration 1Deep Mind, London 2VGG, Department of Engineering Science, University of Oxford
Pseudocode No The information is insufficient as the paper does not contain structured pseudocode or algorithm blocks (clearly labeled algorithm sections or code-like formatted procedures).
Open Source Code Yes Code for the model is available at: https://github. com/deepmind/deepmind-research/tree/master/transporter.
Open Datasets Yes Datasets. We evaluate our method on Atari ALE [1] and Manipulator [35] domains.
Dataset Splits No We train all the methods for 10^6 optimization steps and pick the best model checkpoint based on a validation set. The information is insufficient as it does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for the validation set.
Hardware Specification No The information is insufficient as the paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The information is insufficient as the paper does not provide specific ancillary software details (e.g., library or solver names with version numbers like Python 3.8, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup No For implementation details, please refer to the supplementary material. The information is insufficient as the paper defers experimental setup details to supplementary materials rather than providing them in the main text.