Regression Planning Networks

Authors: Danfei Xu, Roberto Martín-Martín, De-An Huang, Yuke Zhu, Silvio Savarese, Li F. Fei-Fei

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the capabilities of RPN in a grid world environment and a simulated 3D kitchen environment featuring complex visual scene and long task horizon, and show that it achieves near-optimal performance in completely new task instances.
Researcher Affiliation Academia Danfei Xu Stanford University Roberto Martín-Martín Stanford University De-An Huang Stanford University Yuke Zhu Stanford University Silvio Savarese Stanford University Li Fei-Fei Stanford University
Pseudocode Yes Algorithm 1 SUBGOALSERIALIZATION
Open Source Code No The paper does not provide a direct link to the source code for the described methodology or state that it is publicly available in supplementary materials or elsewhere.
Open Datasets No The paper mentions environments like 'Grid World' and 'Kitchen 3D' and describes training tasks (e.g., 'training tasks are to cook randomly chosen I = 3 ingredients into D = 2 dishes') but does not provide concrete access information (link, DOI, citation with authors/year for a public dataset) for these environments or the data generated within them.
Dataset Splits No The paper mentions 'training tasks' and 'evaluation tasks' but does not specify the dataset splits (e.g., percentages or sample counts) for train, validation, or test sets. It implies a split by referring to 'training tasks' and 'evaluation tasks' but lacks specific details for reproducibility.
Hardware Specification No The paper states that the Kitchen 3D environment is 'simulated with [34]' but does not provide any specific hardware details (e.g., GPU models, CPU types, memory) used for running the simulations or training the models.
Software Dependencies No The paper mentions 'pybullet, a python module for physics simulation, games, robotics and machine learning. http://pybullet.org/, 2016 2017' as a reference, but it does not explicitly state the version numbers of any other software dependencies like Python, PyTorch, TensorFlow, or other libraries used in the implementation.
Experiment Setup No The paper mentions 'More details on network architectures and evaluation setup are available in the Appendix' and 'More details is included in the Appendix' but does not provide specific hyperparameters or system-level training settings within the main text.