The Logical Options Framework

Authors: Brandon Araki, Xiao Li, Kiran Vodrahalli, Jonathan Decastro, Micah Fry, Daniela Rus

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate LOF on four tasks in discrete and continuous domains, including a 3D pick-and-place environment.
Researcher Affiliation Collaboration 1CSAIL, Massachusetts Institute of Technology, Cambridge, MA, USA 2Department of Computer Science, Columbia Univer sity, New York City, NY, USA 3Toyota Research Institute, Cam bridge, MA, USA 4MIT Lincoln Laboratory, Lexington, MA, USA.
Pseudocode Yes Algorithm 1 Learning and Planning with Logical Options
Open Source Code Yes Code for the discrete domain experiments is available at https://github.com/braraki/ logical-options-framework. Code for the other domains is available in the supplementary material.
Open Datasets Yes The second environment is called the reacher domain, from Open AI Gym (Fig. 3d). ... The third en vironment is called the pick-and-place domain, and it is a continuous 3D environment with a robotic Panda arm from Coppelia Sim and Py Rep (James et al., 2019).
Dataset Splits No The paper describes its experimental environments and tasks, but it does not specify explicit training, validation, or test dataset splits in terms of percentages or sample counts.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU/GPU models, memory specifications) used for running the experiments.
Software Dependencies No The paper mentions algorithms and frameworks like Q-learning, PPO, Deep-QRM, but does not list specific software dependencies with version numbers (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup No The implementa tion details are discussed more fully in App. C.