Object-Oriented Dynamics Predictor

Authors: Guangxiang Zhu, Zhiao Huang, Chongjie Zhang

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

Reproducibility Variable Result LLM Response
Research Type Experimental Empirical results show that OODP significantly outperforms previous methods in terms of generalization over novel environments with various object layouts.
Researcher Affiliation Academia Guangxiang Zhu, Zhiao Huang, and Chongjie Zhang Institute for Interdisciplinary Information Sciences Tsinghua University, Beijing, China guangxiangzhu@outlook.com,hza14@mails.tsinghua.edu.cn,chongjie@tsinghua.edu.cn
Pseudocode No The paper describes the methodology with figures and text, but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes The code of OODP is available online at https://github.com/mig-zh/OODP.
Open Datasets Yes We evaluate our model on Monster Kong from the Pygame Learning Environment [36], which offers various scenes for testing generalization abilities across object layouts (e.g., different number and spatial arrangement of objects).
Dataset Splits No The paper describes using 'k training environments' and 'm unseen testing environments' for zero-shot generalization problems but does not specify training/validation/test splits or a validation set.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers used for the experiments.
Experiment Setup No The paper describes the model architecture and losses but does not provide specific experimental setup details like hyperparameter values (e.g., learning rate, batch size, epochs) or optimizer settings.